| [2025-01-07 20:28:26,226][00160] Saving configuration to /content/train_dir/default_experiment/config.json... | |
| [2025-01-07 20:28:26,230][00160] Rollout worker 0 uses device cpu | |
| [2025-01-07 20:28:26,231][00160] Rollout worker 1 uses device cpu | |
| [2025-01-07 20:28:26,232][00160] Rollout worker 2 uses device cpu | |
| [2025-01-07 20:28:26,233][00160] Rollout worker 3 uses device cpu | |
| [2025-01-07 20:28:26,234][00160] Rollout worker 4 uses device cpu | |
| [2025-01-07 20:28:26,235][00160] Rollout worker 5 uses device cpu | |
| [2025-01-07 20:28:26,236][00160] Rollout worker 6 uses device cpu | |
| [2025-01-07 20:28:26,237][00160] Rollout worker 7 uses device cpu | |
| [2025-01-07 20:28:26,388][00160] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2025-01-07 20:28:26,389][00160] InferenceWorker_p0-w0: min num requests: 2 | |
| [2025-01-07 20:28:26,423][00160] Starting all processes... | |
| [2025-01-07 20:28:26,424][00160] Starting process learner_proc0 | |
| [2025-01-07 20:28:26,470][00160] Starting all processes... | |
| [2025-01-07 20:28:26,477][00160] Starting process inference_proc0-0 | |
| [2025-01-07 20:28:26,479][00160] Starting process rollout_proc1 | |
| [2025-01-07 20:28:26,478][00160] Starting process rollout_proc0 | |
| [2025-01-07 20:28:26,480][00160] Starting process rollout_proc2 | |
| [2025-01-07 20:28:26,480][00160] Starting process rollout_proc3 | |
| [2025-01-07 20:28:26,480][00160] Starting process rollout_proc4 | |
| [2025-01-07 20:28:26,480][00160] Starting process rollout_proc5 | |
| [2025-01-07 20:28:26,480][00160] Starting process rollout_proc6 | |
| [2025-01-07 20:28:26,480][00160] Starting process rollout_proc7 | |
| [2025-01-07 20:28:43,473][03288] Worker 6 uses CPU cores [0] | |
| [2025-01-07 20:28:43,568][03286] Worker 4 uses CPU cores [0] | |
| [2025-01-07 20:28:43,960][03281] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2025-01-07 20:28:43,959][03285] Worker 3 uses CPU cores [1] | |
| [2025-01-07 20:28:43,967][03281] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 | |
| [2025-01-07 20:28:43,988][03282] Worker 1 uses CPU cores [1] | |
| [2025-01-07 20:28:43,988][03268] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2025-01-07 20:28:43,995][03268] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 | |
| [2025-01-07 20:28:44,037][03281] Num visible devices: 1 | |
| [2025-01-07 20:28:44,056][03268] Num visible devices: 1 | |
| [2025-01-07 20:28:44,079][03268] Starting seed is not provided | |
| [2025-01-07 20:28:44,080][03268] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2025-01-07 20:28:44,081][03268] Initializing actor-critic model on device cuda:0 | |
| [2025-01-07 20:28:44,082][03268] RunningMeanStd input shape: (3, 72, 128) | |
| [2025-01-07 20:28:44,085][03268] RunningMeanStd input shape: (1,) | |
| [2025-01-07 20:28:44,118][03283] Worker 0 uses CPU cores [0] | |
| [2025-01-07 20:28:44,127][03284] Worker 2 uses CPU cores [0] | |
| [2025-01-07 20:28:44,132][03268] ConvEncoder: input_channels=3 | |
| [2025-01-07 20:28:44,149][03289] Worker 7 uses CPU cores [1] | |
| [2025-01-07 20:28:44,155][03287] Worker 5 uses CPU cores [1] | |
| [2025-01-07 20:28:44,410][03268] Conv encoder output size: 512 | |
| [2025-01-07 20:28:44,411][03268] Policy head output size: 512 | |
| [2025-01-07 20:28:44,471][03268] Created Actor Critic model with architecture: | |
| [2025-01-07 20:28:44,471][03268] ActorCriticSharedWeights( | |
| (obs_normalizer): ObservationNormalizer( | |
| (running_mean_std): RunningMeanStdDictInPlace( | |
| (running_mean_std): ModuleDict( | |
| (obs): RunningMeanStdInPlace() | |
| ) | |
| ) | |
| ) | |
| (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) | |
| (encoder): VizdoomEncoder( | |
| (basic_encoder): ConvEncoder( | |
| (enc): RecursiveScriptModule( | |
| original_name=ConvEncoderImpl | |
| (conv_head): RecursiveScriptModule( | |
| original_name=Sequential | |
| (0): RecursiveScriptModule(original_name=Conv2d) | |
| (1): RecursiveScriptModule(original_name=ELU) | |
| (2): RecursiveScriptModule(original_name=Conv2d) | |
| (3): RecursiveScriptModule(original_name=ELU) | |
| (4): RecursiveScriptModule(original_name=Conv2d) | |
| (5): RecursiveScriptModule(original_name=ELU) | |
| ) | |
| (mlp_layers): RecursiveScriptModule( | |
| original_name=Sequential | |
| (0): RecursiveScriptModule(original_name=Linear) | |
| (1): RecursiveScriptModule(original_name=ELU) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (core): ModelCoreRNN( | |
| (core): GRU(512, 512) | |
| ) | |
| (decoder): MlpDecoder( | |
| (mlp): Identity() | |
| ) | |
| (critic_linear): Linear(in_features=512, out_features=1, bias=True) | |
| (action_parameterization): ActionParameterizationDefault( | |
| (distribution_linear): Linear(in_features=512, out_features=5, bias=True) | |
| ) | |
| ) | |
| [2025-01-07 20:28:44,859][03268] Using optimizer <class 'torch.optim.adam.Adam'> | |
| [2025-01-07 20:28:46,382][00160] Heartbeat connected on Batcher_0 | |
| [2025-01-07 20:28:46,394][00160] Heartbeat connected on InferenceWorker_p0-w0 | |
| [2025-01-07 20:28:46,402][00160] Heartbeat connected on RolloutWorker_w1 | |
| [2025-01-07 20:28:46,403][00160] Heartbeat connected on RolloutWorker_w0 | |
| [2025-01-07 20:28:46,405][00160] Heartbeat connected on RolloutWorker_w2 | |
| [2025-01-07 20:28:46,411][00160] Heartbeat connected on RolloutWorker_w3 | |
| [2025-01-07 20:28:46,413][00160] Heartbeat connected on RolloutWorker_w4 | |
| [2025-01-07 20:28:46,417][00160] Heartbeat connected on RolloutWorker_w5 | |
| [2025-01-07 20:28:46,427][00160] Heartbeat connected on RolloutWorker_w7 | |
| [2025-01-07 20:28:46,429][00160] Heartbeat connected on RolloutWorker_w6 | |
| [2025-01-07 20:28:49,473][03268] No checkpoints found | |
| [2025-01-07 20:28:49,473][03268] Did not load from checkpoint, starting from scratch! | |
| [2025-01-07 20:28:49,474][03268] Initialized policy 0 weights for model version 0 | |
| [2025-01-07 20:28:49,478][03268] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2025-01-07 20:28:49,485][03268] LearnerWorker_p0 finished initialization! | |
| [2025-01-07 20:28:49,486][00160] Heartbeat connected on LearnerWorker_p0 | |
| [2025-01-07 20:28:49,672][03281] RunningMeanStd input shape: (3, 72, 128) | |
| [2025-01-07 20:28:49,673][03281] RunningMeanStd input shape: (1,) | |
| [2025-01-07 20:28:49,685][03281] ConvEncoder: input_channels=3 | |
| [2025-01-07 20:28:49,789][03281] Conv encoder output size: 512 | |
| [2025-01-07 20:28:49,790][03281] Policy head output size: 512 | |
| [2025-01-07 20:28:49,902][00160] Inference worker 0-0 is ready! | |
| [2025-01-07 20:28:49,911][00160] All inference workers are ready! Signal rollout workers to start! | |
| [2025-01-07 20:28:50,161][03282] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-01-07 20:28:50,167][03285] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-01-07 20:28:50,163][03287] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-01-07 20:28:50,168][03289] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-01-07 20:28:50,178][03283] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-01-07 20:28:50,171][03284] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-01-07 20:28:50,182][03288] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-01-07 20:28:50,186][03286] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-01-07 20:28:50,505][00160] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2025-01-07 20:28:51,614][03286] Decorrelating experience for 0 frames... | |
| [2025-01-07 20:28:51,613][03284] Decorrelating experience for 0 frames... | |
| [2025-01-07 20:28:51,612][03285] Decorrelating experience for 0 frames... | |
| [2025-01-07 20:28:51,614][03289] Decorrelating experience for 0 frames... | |
| [2025-01-07 20:28:51,612][03282] Decorrelating experience for 0 frames... | |
| [2025-01-07 20:28:51,750][03288] Decorrelating experience for 0 frames... | |
| [2025-01-07 20:28:52,354][03284] Decorrelating experience for 32 frames... | |
| [2025-01-07 20:28:52,608][03288] Decorrelating experience for 32 frames... | |
| [2025-01-07 20:28:52,801][03287] Decorrelating experience for 0 frames... | |
| [2025-01-07 20:28:52,814][03282] Decorrelating experience for 32 frames... | |
| [2025-01-07 20:28:52,824][03285] Decorrelating experience for 32 frames... | |
| [2025-01-07 20:28:53,478][03286] Decorrelating experience for 32 frames... | |
| [2025-01-07 20:28:54,134][03288] Decorrelating experience for 64 frames... | |
| [2025-01-07 20:28:54,418][03284] Decorrelating experience for 64 frames... | |
| [2025-01-07 20:28:54,670][03287] Decorrelating experience for 32 frames... | |
| [2025-01-07 20:28:54,692][03289] Decorrelating experience for 32 frames... | |
| [2025-01-07 20:28:55,123][03285] Decorrelating experience for 64 frames... | |
| [2025-01-07 20:28:55,130][03282] Decorrelating experience for 64 frames... | |
| [2025-01-07 20:28:55,505][00160] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2025-01-07 20:28:55,940][03288] Decorrelating experience for 96 frames... | |
| [2025-01-07 20:28:55,999][03289] Decorrelating experience for 64 frames... | |
| [2025-01-07 20:28:56,018][03286] Decorrelating experience for 64 frames... | |
| [2025-01-07 20:28:56,059][03285] Decorrelating experience for 96 frames... | |
| [2025-01-07 20:28:57,081][03284] Decorrelating experience for 96 frames... | |
| [2025-01-07 20:28:57,104][03287] Decorrelating experience for 64 frames... | |
| [2025-01-07 20:28:57,173][03289] Decorrelating experience for 96 frames... | |
| [2025-01-07 20:28:57,333][03286] Decorrelating experience for 96 frames... | |
| [2025-01-07 20:28:57,917][03282] Decorrelating experience for 96 frames... | |
| [2025-01-07 20:28:57,990][03287] Decorrelating experience for 96 frames... | |
| [2025-01-07 20:29:00,505][00160] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 63.8. Samples: 638. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2025-01-07 20:29:00,511][00160] Avg episode reward: [(0, '1.565')] | |
| [2025-01-07 20:29:02,632][03268] Signal inference workers to stop experience collection... | |
| [2025-01-07 20:29:02,665][03281] InferenceWorker_p0-w0: stopping experience collection | |
| [2025-01-07 20:29:05,505][00160] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 163.3. Samples: 2450. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2025-01-07 20:29:05,511][00160] Avg episode reward: [(0, '2.386')] | |
| [2025-01-07 20:29:06,457][03268] Signal inference workers to resume experience collection... | |
| [2025-01-07 20:29:06,459][03281] InferenceWorker_p0-w0: resuming experience collection | |
| [2025-01-07 20:29:10,505][00160] Fps is (10 sec: 2048.0, 60 sec: 1024.0, 300 sec: 1024.0). Total num frames: 20480. Throughput: 0: 180.5. Samples: 3610. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:29:10,511][00160] Avg episode reward: [(0, '3.541')] | |
| [2025-01-07 20:29:14,671][03281] Updated weights for policy 0, policy_version 10 (0.0164) | |
| [2025-01-07 20:29:15,506][00160] Fps is (10 sec: 4095.6, 60 sec: 1638.3, 300 sec: 1638.3). Total num frames: 40960. Throughput: 0: 402.7. Samples: 10068. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2025-01-07 20:29:15,509][00160] Avg episode reward: [(0, '4.296')] | |
| [2025-01-07 20:29:20,508][00160] Fps is (10 sec: 3685.5, 60 sec: 1911.3, 300 sec: 1911.3). Total num frames: 57344. Throughput: 0: 486.0. Samples: 14582. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-07 20:29:20,518][00160] Avg episode reward: [(0, '4.534')] | |
| [2025-01-07 20:29:25,505][00160] Fps is (10 sec: 3277.1, 60 sec: 2106.5, 300 sec: 2106.5). Total num frames: 73728. Throughput: 0: 483.4. Samples: 16920. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2025-01-07 20:29:25,512][00160] Avg episode reward: [(0, '4.328')] | |
| [2025-01-07 20:29:26,719][03281] Updated weights for policy 0, policy_version 20 (0.0022) | |
| [2025-01-07 20:29:30,505][00160] Fps is (10 sec: 4097.0, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 98304. Throughput: 0: 585.2. Samples: 23406. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-07 20:29:30,507][00160] Avg episode reward: [(0, '4.298')] | |
| [2025-01-07 20:29:35,506][00160] Fps is (10 sec: 3686.3, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 110592. Throughput: 0: 636.0. Samples: 28622. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:29:35,509][00160] Avg episode reward: [(0, '4.451')] | |
| [2025-01-07 20:29:35,514][03268] Saving new best policy, reward=4.451! | |
| [2025-01-07 20:29:38,813][03281] Updated weights for policy 0, policy_version 30 (0.0017) | |
| [2025-01-07 20:29:40,505][00160] Fps is (10 sec: 3276.8, 60 sec: 2621.4, 300 sec: 2621.4). Total num frames: 131072. Throughput: 0: 679.0. Samples: 30554. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-07 20:29:40,510][00160] Avg episode reward: [(0, '4.387')] | |
| [2025-01-07 20:29:45,505][00160] Fps is (10 sec: 4096.1, 60 sec: 2755.5, 300 sec: 2755.5). Total num frames: 151552. Throughput: 0: 805.7. Samples: 36894. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-01-07 20:29:45,508][00160] Avg episode reward: [(0, '4.261')] | |
| [2025-01-07 20:29:48,112][03281] Updated weights for policy 0, policy_version 40 (0.0018) | |
| [2025-01-07 20:29:50,506][00160] Fps is (10 sec: 3686.0, 60 sec: 2798.9, 300 sec: 2798.9). Total num frames: 167936. Throughput: 0: 896.3. Samples: 42786. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-07 20:29:50,509][00160] Avg episode reward: [(0, '4.310')] | |
| [2025-01-07 20:29:55,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 2835.7). Total num frames: 184320. Throughput: 0: 915.2. Samples: 44792. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:29:55,508][00160] Avg episode reward: [(0, '4.300')] | |
| [2025-01-07 20:30:00,161][03281] Updated weights for policy 0, policy_version 50 (0.0027) | |
| [2025-01-07 20:30:00,505][00160] Fps is (10 sec: 3686.8, 60 sec: 3413.3, 300 sec: 2925.7). Total num frames: 204800. Throughput: 0: 895.4. Samples: 50362. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:30:00,507][00160] Avg episode reward: [(0, '4.356')] | |
| [2025-01-07 20:30:05,508][00160] Fps is (10 sec: 4094.9, 60 sec: 3754.5, 300 sec: 3003.6). Total num frames: 225280. Throughput: 0: 936.8. Samples: 56740. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-01-07 20:30:05,513][00160] Avg episode reward: [(0, '4.389')] | |
| [2025-01-07 20:30:10,507][00160] Fps is (10 sec: 3276.4, 60 sec: 3618.1, 300 sec: 2969.6). Total num frames: 237568. Throughput: 0: 930.9. Samples: 58810. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:30:10,509][00160] Avg episode reward: [(0, '4.435')] | |
| [2025-01-07 20:30:12,259][03281] Updated weights for policy 0, policy_version 60 (0.0041) | |
| [2025-01-07 20:30:15,505][00160] Fps is (10 sec: 3277.7, 60 sec: 3618.2, 300 sec: 3035.9). Total num frames: 258048. Throughput: 0: 893.9. Samples: 63630. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:30:15,508][00160] Avg episode reward: [(0, '4.259')] | |
| [2025-01-07 20:30:20,505][00160] Fps is (10 sec: 4096.5, 60 sec: 3686.5, 300 sec: 3094.8). Total num frames: 278528. Throughput: 0: 923.3. Samples: 70172. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-01-07 20:30:20,512][00160] Avg episode reward: [(0, '4.133')] | |
| [2025-01-07 20:30:20,519][03268] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000068_278528.pth... | |
| [2025-01-07 20:30:21,746][03281] Updated weights for policy 0, policy_version 70 (0.0035) | |
| [2025-01-07 20:30:25,507][00160] Fps is (10 sec: 3685.7, 60 sec: 3686.3, 300 sec: 3104.3). Total num frames: 294912. Throughput: 0: 944.0. Samples: 73034. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-07 20:30:25,512][00160] Avg episode reward: [(0, '4.291')] | |
| [2025-01-07 20:30:30,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3113.0). Total num frames: 311296. Throughput: 0: 891.9. Samples: 77028. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:30:30,508][00160] Avg episode reward: [(0, '4.329')] | |
| [2025-01-07 20:30:33,946][03281] Updated weights for policy 0, policy_version 80 (0.0019) | |
| [2025-01-07 20:30:35,506][00160] Fps is (10 sec: 3687.0, 60 sec: 3686.4, 300 sec: 3159.8). Total num frames: 331776. Throughput: 0: 903.3. Samples: 83434. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:30:35,512][00160] Avg episode reward: [(0, '4.605')] | |
| [2025-01-07 20:30:35,517][03268] Saving new best policy, reward=4.605! | |
| [2025-01-07 20:30:40,505][00160] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3202.3). Total num frames: 352256. Throughput: 0: 930.0. Samples: 86642. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-07 20:30:40,510][00160] Avg episode reward: [(0, '4.665')] | |
| [2025-01-07 20:30:40,519][03268] Saving new best policy, reward=4.665! | |
| [2025-01-07 20:30:45,505][00160] Fps is (10 sec: 3276.9, 60 sec: 3549.9, 300 sec: 3169.9). Total num frames: 364544. Throughput: 0: 899.6. Samples: 90842. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2025-01-07 20:30:45,515][00160] Avg episode reward: [(0, '4.608')] | |
| [2025-01-07 20:30:46,048][03281] Updated weights for policy 0, policy_version 90 (0.0037) | |
| [2025-01-07 20:30:50,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3618.2, 300 sec: 3208.5). Total num frames: 385024. Throughput: 0: 888.6. Samples: 96726. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:30:50,513][00160] Avg episode reward: [(0, '4.523')] | |
| [2025-01-07 20:30:55,451][03281] Updated weights for policy 0, policy_version 100 (0.0024) | |
| [2025-01-07 20:30:55,508][00160] Fps is (10 sec: 4504.3, 60 sec: 3754.5, 300 sec: 3276.7). Total num frames: 409600. Throughput: 0: 916.2. Samples: 100042. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2025-01-07 20:30:55,517][00160] Avg episode reward: [(0, '4.381')] | |
| [2025-01-07 20:31:00,506][00160] Fps is (10 sec: 3686.3, 60 sec: 3618.1, 300 sec: 3245.3). Total num frames: 421888. Throughput: 0: 919.9. Samples: 105024. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2025-01-07 20:31:00,510][00160] Avg episode reward: [(0, '4.308')] | |
| [2025-01-07 20:31:05,505][00160] Fps is (10 sec: 2868.0, 60 sec: 3550.0, 300 sec: 3246.5). Total num frames: 438272. Throughput: 0: 886.9. Samples: 110082. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:31:05,512][00160] Avg episode reward: [(0, '4.518')] | |
| [2025-01-07 20:31:07,662][03281] Updated weights for policy 0, policy_version 110 (0.0019) | |
| [2025-01-07 20:31:10,505][00160] Fps is (10 sec: 3686.5, 60 sec: 3686.5, 300 sec: 3276.8). Total num frames: 458752. Throughput: 0: 896.8. Samples: 113388. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-07 20:31:10,512][00160] Avg episode reward: [(0, '4.614')] | |
| [2025-01-07 20:31:15,506][00160] Fps is (10 sec: 3686.0, 60 sec: 3618.1, 300 sec: 3276.8). Total num frames: 475136. Throughput: 0: 934.7. Samples: 119092. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:31:15,512][00160] Avg episode reward: [(0, '4.688')] | |
| [2025-01-07 20:31:15,516][03268] Saving new best policy, reward=4.688! | |
| [2025-01-07 20:31:19,719][03281] Updated weights for policy 0, policy_version 120 (0.0018) | |
| [2025-01-07 20:31:20,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3276.8). Total num frames: 491520. Throughput: 0: 891.2. Samples: 123536. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:31:20,508][00160] Avg episode reward: [(0, '4.534')] | |
| [2025-01-07 20:31:25,505][00160] Fps is (10 sec: 4096.4, 60 sec: 3686.5, 300 sec: 3329.7). Total num frames: 516096. Throughput: 0: 892.6. Samples: 126808. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0) | |
| [2025-01-07 20:31:25,510][00160] Avg episode reward: [(0, '4.503')] | |
| [2025-01-07 20:31:29,352][03281] Updated weights for policy 0, policy_version 130 (0.0020) | |
| [2025-01-07 20:31:30,505][00160] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3328.0). Total num frames: 532480. Throughput: 0: 941.6. Samples: 133212. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:31:30,512][00160] Avg episode reward: [(0, '4.465')] | |
| [2025-01-07 20:31:35,508][00160] Fps is (10 sec: 2866.6, 60 sec: 3549.8, 300 sec: 3301.6). Total num frames: 544768. Throughput: 0: 899.2. Samples: 137190. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:31:35,512][00160] Avg episode reward: [(0, '4.415')] | |
| [2025-01-07 20:31:40,505][00160] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3349.1). Total num frames: 569344. Throughput: 0: 891.8. Samples: 140172. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-01-07 20:31:40,512][00160] Avg episode reward: [(0, '4.395')] | |
| [2025-01-07 20:31:41,285][03281] Updated weights for policy 0, policy_version 140 (0.0015) | |
| [2025-01-07 20:31:45,505][00160] Fps is (10 sec: 4506.6, 60 sec: 3754.7, 300 sec: 3370.4). Total num frames: 589824. Throughput: 0: 928.3. Samples: 146796. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:31:45,508][00160] Avg episode reward: [(0, '4.196')] | |
| [2025-01-07 20:31:50,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3345.1). Total num frames: 602112. Throughput: 0: 919.2. Samples: 151446. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:31:50,507][00160] Avg episode reward: [(0, '4.488')] | |
| [2025-01-07 20:31:53,020][03281] Updated weights for policy 0, policy_version 150 (0.0030) | |
| [2025-01-07 20:31:55,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3550.0, 300 sec: 3365.4). Total num frames: 622592. Throughput: 0: 900.0. Samples: 153888. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:31:55,512][00160] Avg episode reward: [(0, '4.593')] | |
| [2025-01-07 20:32:00,505][00160] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3384.6). Total num frames: 643072. Throughput: 0: 920.9. Samples: 160530. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:32:00,512][00160] Avg episode reward: [(0, '4.664')] | |
| [2025-01-07 20:32:02,588][03281] Updated weights for policy 0, policy_version 160 (0.0019) | |
| [2025-01-07 20:32:05,505][00160] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3381.8). Total num frames: 659456. Throughput: 0: 941.4. Samples: 165900. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:32:05,511][00160] Avg episode reward: [(0, '4.449')] | |
| [2025-01-07 20:32:10,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3379.2). Total num frames: 675840. Throughput: 0: 912.7. Samples: 167878. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:32:10,510][00160] Avg episode reward: [(0, '4.453')] | |
| [2025-01-07 20:32:14,374][03281] Updated weights for policy 0, policy_version 170 (0.0019) | |
| [2025-01-07 20:32:15,505][00160] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3416.7). Total num frames: 700416. Throughput: 0: 906.6. Samples: 174008. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-01-07 20:32:15,512][00160] Avg episode reward: [(0, '4.477')] | |
| [2025-01-07 20:32:20,505][00160] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3432.8). Total num frames: 720896. Throughput: 0: 957.2. Samples: 180262. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2025-01-07 20:32:20,513][00160] Avg episode reward: [(0, '4.561')] | |
| [2025-01-07 20:32:20,528][03268] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000176_720896.pth... | |
| [2025-01-07 20:32:25,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3410.2). Total num frames: 733184. Throughput: 0: 933.0. Samples: 182156. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:32:25,513][00160] Avg episode reward: [(0, '4.584')] | |
| [2025-01-07 20:32:26,368][03281] Updated weights for policy 0, policy_version 180 (0.0035) | |
| [2025-01-07 20:32:30,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3425.7). Total num frames: 753664. Throughput: 0: 908.9. Samples: 187696. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:32:30,508][00160] Avg episode reward: [(0, '4.569')] | |
| [2025-01-07 20:32:35,505][00160] Fps is (10 sec: 4096.0, 60 sec: 3823.1, 300 sec: 3440.6). Total num frames: 774144. Throughput: 0: 949.6. Samples: 194180. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:32:35,510][00160] Avg episode reward: [(0, '4.301')] | |
| [2025-01-07 20:32:35,674][03281] Updated weights for policy 0, policy_version 190 (0.0022) | |
| [2025-01-07 20:32:40,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3419.3). Total num frames: 786432. Throughput: 0: 946.0. Samples: 196456. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-01-07 20:32:40,510][00160] Avg episode reward: [(0, '4.368')] | |
| [2025-01-07 20:32:45,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3433.7). Total num frames: 806912. Throughput: 0: 906.0. Samples: 201300. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-01-07 20:32:45,512][00160] Avg episode reward: [(0, '4.577')] | |
| [2025-01-07 20:32:47,472][03281] Updated weights for policy 0, policy_version 200 (0.0019) | |
| [2025-01-07 20:32:50,505][00160] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3464.5). Total num frames: 831488. Throughput: 0: 934.6. Samples: 207958. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:32:50,508][00160] Avg episode reward: [(0, '4.529')] | |
| [2025-01-07 20:32:55,505][00160] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3460.7). Total num frames: 847872. Throughput: 0: 956.8. Samples: 210932. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2025-01-07 20:32:55,508][00160] Avg episode reward: [(0, '4.532')] | |
| [2025-01-07 20:32:59,382][03281] Updated weights for policy 0, policy_version 210 (0.0025) | |
| [2025-01-07 20:33:00,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3457.0). Total num frames: 864256. Throughput: 0: 912.1. Samples: 215054. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:33:00,511][00160] Avg episode reward: [(0, '4.398')] | |
| [2025-01-07 20:33:05,505][00160] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3469.6). Total num frames: 884736. Throughput: 0: 917.8. Samples: 221564. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:33:05,508][00160] Avg episode reward: [(0, '4.415')] | |
| [2025-01-07 20:33:08,785][03281] Updated weights for policy 0, policy_version 220 (0.0014) | |
| [2025-01-07 20:33:10,505][00160] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3481.6). Total num frames: 905216. Throughput: 0: 948.4. Samples: 224834. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-07 20:33:10,508][00160] Avg episode reward: [(0, '4.545')] | |
| [2025-01-07 20:33:15,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3462.3). Total num frames: 917504. Throughput: 0: 920.1. Samples: 229100. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2025-01-07 20:33:15,507][00160] Avg episode reward: [(0, '4.491')] | |
| [2025-01-07 20:33:20,510][00160] Fps is (10 sec: 3275.3, 60 sec: 3617.9, 300 sec: 3474.0). Total num frames: 937984. Throughput: 0: 912.9. Samples: 235266. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:33:20,516][00160] Avg episode reward: [(0, '4.498')] | |
| [2025-01-07 20:33:20,607][03281] Updated weights for policy 0, policy_version 230 (0.0021) | |
| [2025-01-07 20:33:25,508][00160] Fps is (10 sec: 4504.3, 60 sec: 3822.7, 300 sec: 3500.2). Total num frames: 962560. Throughput: 0: 935.7. Samples: 238564. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-01-07 20:33:25,511][00160] Avg episode reward: [(0, '4.317')] | |
| [2025-01-07 20:33:30,505][00160] Fps is (10 sec: 3688.1, 60 sec: 3686.4, 300 sec: 3481.6). Total num frames: 974848. Throughput: 0: 936.8. Samples: 243458. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:33:30,512][00160] Avg episode reward: [(0, '4.500')] | |
| [2025-01-07 20:33:32,465][03281] Updated weights for policy 0, policy_version 240 (0.0030) | |
| [2025-01-07 20:33:35,505][00160] Fps is (10 sec: 3277.8, 60 sec: 3686.4, 300 sec: 3492.4). Total num frames: 995328. Throughput: 0: 906.0. Samples: 248730. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-01-07 20:33:35,508][00160] Avg episode reward: [(0, '4.812')] | |
| [2025-01-07 20:33:35,511][03268] Saving new best policy, reward=4.812! | |
| [2025-01-07 20:33:40,505][00160] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3502.8). Total num frames: 1015808. Throughput: 0: 911.0. Samples: 251926. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:33:40,508][00160] Avg episode reward: [(0, '4.824')] | |
| [2025-01-07 20:33:40,518][03268] Saving new best policy, reward=4.824! | |
| [2025-01-07 20:33:42,648][03281] Updated weights for policy 0, policy_version 250 (0.0026) | |
| [2025-01-07 20:33:45,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3485.1). Total num frames: 1028096. Throughput: 0: 940.2. Samples: 257362. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:33:45,511][00160] Avg episode reward: [(0, '4.724')] | |
| [2025-01-07 20:33:50,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3554.5). Total num frames: 1048576. Throughput: 0: 899.7. Samples: 262052. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:33:50,512][00160] Avg episode reward: [(0, '4.811')] | |
| [2025-01-07 20:33:54,253][03281] Updated weights for policy 0, policy_version 260 (0.0020) | |
| [2025-01-07 20:33:55,505][00160] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3623.9). Total num frames: 1069056. Throughput: 0: 898.9. Samples: 265286. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:33:55,507][00160] Avg episode reward: [(0, '5.023')] | |
| [2025-01-07 20:33:55,515][03268] Saving new best policy, reward=5.023! | |
| [2025-01-07 20:34:00,506][00160] Fps is (10 sec: 3686.0, 60 sec: 3686.3, 300 sec: 3679.4). Total num frames: 1085440. Throughput: 0: 941.5. Samples: 271468. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:34:00,511][00160] Avg episode reward: [(0, '5.223')] | |
| [2025-01-07 20:34:00,525][03268] Saving new best policy, reward=5.223! | |
| [2025-01-07 20:34:05,508][00160] Fps is (10 sec: 3275.8, 60 sec: 3618.0, 300 sec: 3665.5). Total num frames: 1101824. Throughput: 0: 890.3. Samples: 275330. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:34:05,511][00160] Avg episode reward: [(0, '5.101')] | |
| [2025-01-07 20:34:06,370][03281] Updated weights for policy 0, policy_version 270 (0.0022) | |
| [2025-01-07 20:34:10,505][00160] Fps is (10 sec: 3686.8, 60 sec: 3618.1, 300 sec: 3665.6). Total num frames: 1122304. Throughput: 0: 888.0. Samples: 278520. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:34:10,508][00160] Avg episode reward: [(0, '4.914')] | |
| [2025-01-07 20:34:15,510][00160] Fps is (10 sec: 4095.2, 60 sec: 3754.4, 300 sec: 3679.4). Total num frames: 1142784. Throughput: 0: 926.2. Samples: 285142. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2025-01-07 20:34:15,514][00160] Avg episode reward: [(0, '4.852')] | |
| [2025-01-07 20:34:16,287][03281] Updated weights for policy 0, policy_version 280 (0.0021) | |
| [2025-01-07 20:34:20,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3618.4, 300 sec: 3665.6). Total num frames: 1155072. Throughput: 0: 904.3. Samples: 289424. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:34:20,510][00160] Avg episode reward: [(0, '4.801')] | |
| [2025-01-07 20:34:20,523][03268] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000282_1155072.pth... | |
| [2025-01-07 20:34:20,690][03268] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000068_278528.pth | |
| [2025-01-07 20:34:25,505][00160] Fps is (10 sec: 3278.5, 60 sec: 3550.0, 300 sec: 3651.7). Total num frames: 1175552. Throughput: 0: 888.6. Samples: 291912. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-01-07 20:34:25,511][00160] Avg episode reward: [(0, '4.592')] | |
| [2025-01-07 20:34:28,044][03281] Updated weights for policy 0, policy_version 290 (0.0020) | |
| [2025-01-07 20:34:30,505][00160] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3679.5). Total num frames: 1196032. Throughput: 0: 911.0. Samples: 298358. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:34:30,510][00160] Avg episode reward: [(0, '4.788')] | |
| [2025-01-07 20:34:35,505][00160] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3665.6). Total num frames: 1212416. Throughput: 0: 921.0. Samples: 303496. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:34:35,509][00160] Avg episode reward: [(0, '5.095')] | |
| [2025-01-07 20:34:39,989][03281] Updated weights for policy 0, policy_version 300 (0.0016) | |
| [2025-01-07 20:34:40,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3651.7). Total num frames: 1228800. Throughput: 0: 895.1. Samples: 305566. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:34:40,514][00160] Avg episode reward: [(0, '5.011')] | |
| [2025-01-07 20:34:45,505][00160] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1249280. Throughput: 0: 896.0. Samples: 311786. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2025-01-07 20:34:45,509][00160] Avg episode reward: [(0, '4.839')] | |
| [2025-01-07 20:34:49,943][03281] Updated weights for policy 0, policy_version 310 (0.0013) | |
| [2025-01-07 20:34:50,505][00160] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3679.5). Total num frames: 1269760. Throughput: 0: 943.6. Samples: 317790. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2025-01-07 20:34:50,508][00160] Avg episode reward: [(0, '4.819')] | |
| [2025-01-07 20:34:55,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3651.7). Total num frames: 1282048. Throughput: 0: 915.5. Samples: 319718. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:34:55,512][00160] Avg episode reward: [(0, '4.900')] | |
| [2025-01-07 20:35:00,505][00160] Fps is (10 sec: 3686.4, 60 sec: 3686.5, 300 sec: 3665.6). Total num frames: 1306624. Throughput: 0: 894.4. Samples: 325386. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:35:00,508][00160] Avg episode reward: [(0, '5.025')] | |
| [2025-01-07 20:35:01,379][03281] Updated weights for policy 0, policy_version 320 (0.0014) | |
| [2025-01-07 20:35:05,507][00160] Fps is (10 sec: 4504.7, 60 sec: 3754.7, 300 sec: 3693.3). Total num frames: 1327104. Throughput: 0: 942.3. Samples: 331830. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-07 20:35:05,512][00160] Avg episode reward: [(0, '4.866')] | |
| [2025-01-07 20:35:10,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3665.6). Total num frames: 1339392. Throughput: 0: 931.2. Samples: 333814. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:35:10,508][00160] Avg episode reward: [(0, '4.872')] | |
| [2025-01-07 20:35:13,571][03281] Updated weights for policy 0, policy_version 330 (0.0033) | |
| [2025-01-07 20:35:15,505][00160] Fps is (10 sec: 3277.5, 60 sec: 3618.4, 300 sec: 3665.6). Total num frames: 1359872. Throughput: 0: 898.6. Samples: 338794. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:35:15,512][00160] Avg episode reward: [(0, '4.823')] | |
| [2025-01-07 20:35:20,505][00160] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3679.5). Total num frames: 1380352. Throughput: 0: 929.8. Samples: 345338. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:35:20,508][00160] Avg episode reward: [(0, '5.098')] | |
| [2025-01-07 20:35:23,788][03281] Updated weights for policy 0, policy_version 340 (0.0035) | |
| [2025-01-07 20:35:25,506][00160] Fps is (10 sec: 3686.3, 60 sec: 3686.4, 300 sec: 3679.5). Total num frames: 1396736. Throughput: 0: 946.0. Samples: 348136. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-07 20:35:25,508][00160] Avg episode reward: [(0, '4.959')] | |
| [2025-01-07 20:35:30,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3665.6). Total num frames: 1413120. Throughput: 0: 904.4. Samples: 352482. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:35:30,512][00160] Avg episode reward: [(0, '4.725')] | |
| [2025-01-07 20:35:34,808][03281] Updated weights for policy 0, policy_version 350 (0.0034) | |
| [2025-01-07 20:35:35,505][00160] Fps is (10 sec: 3686.6, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1433600. Throughput: 0: 916.1. Samples: 359014. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:35:35,512][00160] Avg episode reward: [(0, '4.745')] | |
| [2025-01-07 20:35:40,508][00160] Fps is (10 sec: 4095.1, 60 sec: 3754.5, 300 sec: 3693.3). Total num frames: 1454080. Throughput: 0: 944.8. Samples: 362236. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:35:40,510][00160] Avg episode reward: [(0, '4.986')] | |
| [2025-01-07 20:35:45,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3665.6). Total num frames: 1466368. Throughput: 0: 910.0. Samples: 366334. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:35:45,510][00160] Avg episode reward: [(0, '5.360')] | |
| [2025-01-07 20:35:45,516][03268] Saving new best policy, reward=5.360! | |
| [2025-01-07 20:35:46,781][03281] Updated weights for policy 0, policy_version 360 (0.0015) | |
| [2025-01-07 20:35:50,505][00160] Fps is (10 sec: 3687.2, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1490944. Throughput: 0: 906.2. Samples: 372608. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2025-01-07 20:35:50,508][00160] Avg episode reward: [(0, '5.561')] | |
| [2025-01-07 20:35:50,514][03268] Saving new best policy, reward=5.561! | |
| [2025-01-07 20:35:55,505][00160] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3679.5). Total num frames: 1507328. Throughput: 0: 931.4. Samples: 375726. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:35:55,511][00160] Avg episode reward: [(0, '5.220')] | |
| [2025-01-07 20:35:57,283][03281] Updated weights for policy 0, policy_version 370 (0.0027) | |
| [2025-01-07 20:36:00,510][00160] Fps is (10 sec: 3275.2, 60 sec: 3617.8, 300 sec: 3679.4). Total num frames: 1523712. Throughput: 0: 924.9. Samples: 380420. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:36:00,512][00160] Avg episode reward: [(0, '5.049')] | |
| [2025-01-07 20:36:05,505][00160] Fps is (10 sec: 3686.4, 60 sec: 3618.3, 300 sec: 3679.5). Total num frames: 1544192. Throughput: 0: 903.6. Samples: 385998. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:36:05,510][00160] Avg episode reward: [(0, '5.237')] | |
| [2025-01-07 20:36:08,355][03281] Updated weights for policy 0, policy_version 380 (0.0027) | |
| [2025-01-07 20:36:10,505][00160] Fps is (10 sec: 4098.1, 60 sec: 3754.7, 300 sec: 3693.4). Total num frames: 1564672. Throughput: 0: 912.1. Samples: 389178. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:36:10,513][00160] Avg episode reward: [(0, '5.782')] | |
| [2025-01-07 20:36:10,521][03268] Saving new best policy, reward=5.782! | |
| [2025-01-07 20:36:15,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3679.5). Total num frames: 1576960. Throughput: 0: 936.6. Samples: 394628. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:36:15,512][00160] Avg episode reward: [(0, '5.620')] | |
| [2025-01-07 20:36:20,229][03281] Updated weights for policy 0, policy_version 390 (0.0020) | |
| [2025-01-07 20:36:20,507][00160] Fps is (10 sec: 3276.1, 60 sec: 3618.0, 300 sec: 3665.5). Total num frames: 1597440. Throughput: 0: 898.2. Samples: 399434. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:36:20,510][00160] Avg episode reward: [(0, '5.669')] | |
| [2025-01-07 20:36:20,526][03268] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000390_1597440.pth... | |
| [2025-01-07 20:36:20,641][03268] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000176_720896.pth | |
| [2025-01-07 20:36:25,505][00160] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3679.5). Total num frames: 1617920. Throughput: 0: 899.2. Samples: 402696. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:36:25,508][00160] Avg episode reward: [(0, '5.730')] | |
| [2025-01-07 20:36:30,506][00160] Fps is (10 sec: 3687.1, 60 sec: 3686.4, 300 sec: 3693.4). Total num frames: 1634304. Throughput: 0: 943.4. Samples: 408786. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-01-07 20:36:30,508][00160] Avg episode reward: [(0, '5.932')] | |
| [2025-01-07 20:36:30,522][03268] Saving new best policy, reward=5.932! | |
| [2025-01-07 20:36:30,843][03281] Updated weights for policy 0, policy_version 400 (0.0045) | |
| [2025-01-07 20:36:35,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3665.6). Total num frames: 1650688. Throughput: 0: 897.3. Samples: 412986. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:36:35,507][00160] Avg episode reward: [(0, '5.748')] | |
| [2025-01-07 20:36:40,505][00160] Fps is (10 sec: 3686.4, 60 sec: 3618.3, 300 sec: 3665.6). Total num frames: 1671168. Throughput: 0: 898.7. Samples: 416168. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:36:40,512][00160] Avg episode reward: [(0, '5.807')] | |
| [2025-01-07 20:36:41,633][03281] Updated weights for policy 0, policy_version 410 (0.0016) | |
| [2025-01-07 20:36:45,508][00160] Fps is (10 sec: 4094.8, 60 sec: 3754.5, 300 sec: 3693.3). Total num frames: 1691648. Throughput: 0: 940.2. Samples: 422726. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-01-07 20:36:45,513][00160] Avg episode reward: [(0, '6.125')] | |
| [2025-01-07 20:36:45,522][03268] Saving new best policy, reward=6.125! | |
| [2025-01-07 20:36:50,506][00160] Fps is (10 sec: 3276.7, 60 sec: 3549.8, 300 sec: 3665.6). Total num frames: 1703936. Throughput: 0: 908.1. Samples: 426864. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:36:50,509][00160] Avg episode reward: [(0, '6.397')] | |
| [2025-01-07 20:36:50,525][03268] Saving new best policy, reward=6.397! | |
| [2025-01-07 20:36:53,577][03281] Updated weights for policy 0, policy_version 420 (0.0028) | |
| [2025-01-07 20:36:55,505][00160] Fps is (10 sec: 3277.8, 60 sec: 3618.1, 300 sec: 3665.6). Total num frames: 1724416. Throughput: 0: 900.5. Samples: 429700. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2025-01-07 20:36:55,508][00160] Avg episode reward: [(0, '6.180')] | |
| [2025-01-07 20:37:00,505][00160] Fps is (10 sec: 4505.7, 60 sec: 3755.0, 300 sec: 3693.3). Total num frames: 1748992. Throughput: 0: 923.3. Samples: 436176. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:37:00,508][00160] Avg episode reward: [(0, '6.027')] | |
| [2025-01-07 20:37:04,804][03281] Updated weights for policy 0, policy_version 430 (0.0013) | |
| [2025-01-07 20:37:05,505][00160] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3679.5). Total num frames: 1761280. Throughput: 0: 922.7. Samples: 440954. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:37:05,508][00160] Avg episode reward: [(0, '6.501')] | |
| [2025-01-07 20:37:05,509][03268] Saving new best policy, reward=6.501! | |
| [2025-01-07 20:37:10,505][00160] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3651.7). Total num frames: 1777664. Throughput: 0: 894.8. Samples: 442962. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:37:10,512][00160] Avg episode reward: [(0, '6.967')] | |
| [2025-01-07 20:37:10,519][03268] Saving new best policy, reward=6.967! | |
| [2025-01-07 20:37:15,241][03281] Updated weights for policy 0, policy_version 440 (0.0021) | |
| [2025-01-07 20:37:15,505][00160] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3665.6). Total num frames: 1802240. Throughput: 0: 904.7. Samples: 449498. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:37:15,508][00160] Avg episode reward: [(0, '6.650')] | |
| [2025-01-07 20:37:20,505][00160] Fps is (10 sec: 4096.0, 60 sec: 3686.5, 300 sec: 3679.5). Total num frames: 1818624. Throughput: 0: 933.7. Samples: 455004. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:37:20,508][00160] Avg episode reward: [(0, '6.539')] | |
| [2025-01-07 20:37:25,505][00160] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3651.7). Total num frames: 1830912. Throughput: 0: 907.3. Samples: 456996. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-01-07 20:37:25,512][00160] Avg episode reward: [(0, '6.555')] | |
| [2025-01-07 20:37:27,099][03281] Updated weights for policy 0, policy_version 450 (0.0014) | |
| [2025-01-07 20:37:30,505][00160] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1855488. Throughput: 0: 897.5. Samples: 463110. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2025-01-07 20:37:30,511][00160] Avg episode reward: [(0, '7.551')] | |
| [2025-01-07 20:37:30,521][03268] Saving new best policy, reward=7.551! | |
| [2025-01-07 20:37:35,507][00160] Fps is (10 sec: 4504.7, 60 sec: 3754.5, 300 sec: 3693.3). Total num frames: 1875968. Throughput: 0: 942.8. Samples: 469290. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:37:35,512][00160] Avg episode reward: [(0, '7.517')] | |
| [2025-01-07 20:37:38,150][03281] Updated weights for policy 0, policy_version 460 (0.0016) | |
| [2025-01-07 20:37:40,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3665.6). Total num frames: 1888256. Throughput: 0: 923.1. Samples: 471238. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2025-01-07 20:37:40,512][00160] Avg episode reward: [(0, '7.601')] | |
| [2025-01-07 20:37:40,525][03268] Saving new best policy, reward=7.601! | |
| [2025-01-07 20:37:45,506][00160] Fps is (10 sec: 3277.4, 60 sec: 3618.3, 300 sec: 3651.7). Total num frames: 1908736. Throughput: 0: 895.5. Samples: 476472. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:37:45,510][00160] Avg episode reward: [(0, '6.688')] | |
| [2025-01-07 20:37:48,630][03281] Updated weights for policy 0, policy_version 470 (0.0017) | |
| [2025-01-07 20:37:50,505][00160] Fps is (10 sec: 4505.6, 60 sec: 3823.0, 300 sec: 3679.5). Total num frames: 1933312. Throughput: 0: 936.7. Samples: 483104. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2025-01-07 20:37:50,510][00160] Avg episode reward: [(0, '6.735')] | |
| [2025-01-07 20:37:55,509][00160] Fps is (10 sec: 3685.1, 60 sec: 3686.2, 300 sec: 3665.5). Total num frames: 1945600. Throughput: 0: 944.8. Samples: 485482. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:37:55,515][00160] Avg episode reward: [(0, '6.880')] | |
| [2025-01-07 20:38:00,505][00160] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3651.7). Total num frames: 1961984. Throughput: 0: 902.0. Samples: 490090. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:38:00,512][00160] Avg episode reward: [(0, '7.347')] | |
| [2025-01-07 20:38:00,598][03281] Updated weights for policy 0, policy_version 480 (0.0025) | |
| [2025-01-07 20:38:05,505][00160] Fps is (10 sec: 4097.5, 60 sec: 3754.7, 300 sec: 3665.6). Total num frames: 1986560. Throughput: 0: 928.3. Samples: 496776. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-07 20:38:05,515][00160] Avg episode reward: [(0, '7.970')] | |
| [2025-01-07 20:38:05,517][03268] Saving new best policy, reward=7.970! | |
| [2025-01-07 20:38:10,505][00160] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3679.5). Total num frames: 2002944. Throughput: 0: 947.6. Samples: 499636. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:38:10,511][00160] Avg episode reward: [(0, '7.726')] | |
| [2025-01-07 20:38:11,978][03281] Updated weights for policy 0, policy_version 490 (0.0030) | |
| [2025-01-07 20:38:15,506][00160] Fps is (10 sec: 2867.1, 60 sec: 3549.8, 300 sec: 3651.7). Total num frames: 2015232. Throughput: 0: 899.6. Samples: 503592. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-07 20:38:15,510][00160] Avg episode reward: [(0, '8.139')] | |
| [2025-01-07 20:38:15,522][03268] Saving new best policy, reward=8.139! | |
| [2025-01-07 20:38:20,505][00160] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 2039808. Throughput: 0: 904.3. Samples: 509982. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:38:20,508][00160] Avg episode reward: [(0, '7.589')] | |
| [2025-01-07 20:38:20,517][03268] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000498_2039808.pth... | |
| [2025-01-07 20:38:20,639][03268] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000282_1155072.pth | |
| [2025-01-07 20:38:22,336][03281] Updated weights for policy 0, policy_version 500 (0.0024) | |
| [2025-01-07 20:38:25,505][00160] Fps is (10 sec: 4096.1, 60 sec: 3754.7, 300 sec: 3665.6). Total num frames: 2056192. Throughput: 0: 930.8. Samples: 513122. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:38:25,507][00160] Avg episode reward: [(0, '7.541')] | |
| [2025-01-07 20:38:30,505][00160] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 2068480. Throughput: 0: 910.9. Samples: 517462. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:38:30,517][00160] Avg episode reward: [(0, '7.358')] | |
| [2025-01-07 20:38:34,470][03281] Updated weights for policy 0, policy_version 510 (0.0030) | |
| [2025-01-07 20:38:35,506][00160] Fps is (10 sec: 3686.3, 60 sec: 3618.2, 300 sec: 3651.7). Total num frames: 2093056. Throughput: 0: 890.5. Samples: 523176. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-07 20:38:35,508][00160] Avg episode reward: [(0, '7.212')] | |
| [2025-01-07 20:38:40,505][00160] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3679.5). Total num frames: 2113536. Throughput: 0: 909.6. Samples: 526410. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:38:40,513][00160] Avg episode reward: [(0, '8.131')] | |
| [2025-01-07 20:38:45,505][00160] Fps is (10 sec: 3276.9, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 2125824. Throughput: 0: 920.8. Samples: 531528. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:38:45,510][00160] Avg episode reward: [(0, '8.397')] | |
| [2025-01-07 20:38:45,518][03268] Saving new best policy, reward=8.397! | |
| [2025-01-07 20:38:46,140][03281] Updated weights for policy 0, policy_version 520 (0.0016) | |
| [2025-01-07 20:38:50,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3651.7). Total num frames: 2146304. Throughput: 0: 885.5. Samples: 536622. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:38:50,507][00160] Avg episode reward: [(0, '8.824')] | |
| [2025-01-07 20:38:50,523][03268] Saving new best policy, reward=8.824! | |
| [2025-01-07 20:38:55,506][00160] Fps is (10 sec: 4095.9, 60 sec: 3686.6, 300 sec: 3665.6). Total num frames: 2166784. Throughput: 0: 895.0. Samples: 539910. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-01-07 20:38:55,508][00160] Avg episode reward: [(0, '9.186')] | |
| [2025-01-07 20:38:55,511][03268] Saving new best policy, reward=9.186! | |
| [2025-01-07 20:38:56,048][03281] Updated weights for policy 0, policy_version 530 (0.0019) | |
| [2025-01-07 20:39:00,506][00160] Fps is (10 sec: 3686.2, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 2183168. Throughput: 0: 933.3. Samples: 545590. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:39:00,512][00160] Avg episode reward: [(0, '9.382')] | |
| [2025-01-07 20:39:00,526][03268] Saving new best policy, reward=9.382! | |
| [2025-01-07 20:39:05,505][00160] Fps is (10 sec: 3276.9, 60 sec: 3549.9, 300 sec: 3651.7). Total num frames: 2199552. Throughput: 0: 891.4. Samples: 550096. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:39:05,508][00160] Avg episode reward: [(0, '10.568')] | |
| [2025-01-07 20:39:05,511][03268] Saving new best policy, reward=10.568! | |
| [2025-01-07 20:39:08,089][03281] Updated weights for policy 0, policy_version 540 (0.0028) | |
| [2025-01-07 20:39:10,505][00160] Fps is (10 sec: 3686.6, 60 sec: 3618.1, 300 sec: 3651.8). Total num frames: 2220032. Throughput: 0: 891.5. Samples: 553240. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:39:10,508][00160] Avg episode reward: [(0, '11.204')] | |
| [2025-01-07 20:39:10,517][03268] Saving new best policy, reward=11.204! | |
| [2025-01-07 20:39:15,506][00160] Fps is (10 sec: 4095.8, 60 sec: 3754.7, 300 sec: 3679.5). Total num frames: 2240512. Throughput: 0: 937.1. Samples: 559630. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:39:15,513][00160] Avg episode reward: [(0, '11.198')] | |
| [2025-01-07 20:39:20,080][03281] Updated weights for policy 0, policy_version 550 (0.0040) | |
| [2025-01-07 20:39:20,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3651.7). Total num frames: 2252800. Throughput: 0: 900.0. Samples: 563678. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:39:20,512][00160] Avg episode reward: [(0, '11.498')] | |
| [2025-01-07 20:39:20,522][03268] Saving new best policy, reward=11.498! | |
| [2025-01-07 20:39:25,505][00160] Fps is (10 sec: 3277.0, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 2273280. Throughput: 0: 895.6. Samples: 566710. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-07 20:39:25,512][00160] Avg episode reward: [(0, '10.883')] | |
| [2025-01-07 20:39:29,401][03281] Updated weights for policy 0, policy_version 560 (0.0016) | |
| [2025-01-07 20:39:30,505][00160] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3679.5). Total num frames: 2297856. Throughput: 0: 929.6. Samples: 573358. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:39:30,510][00160] Avg episode reward: [(0, '11.400')] | |
| [2025-01-07 20:39:35,509][00160] Fps is (10 sec: 3684.9, 60 sec: 3617.9, 300 sec: 3665.5). Total num frames: 2310144. Throughput: 0: 915.2. Samples: 577808. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2025-01-07 20:39:35,512][00160] Avg episode reward: [(0, '11.445')] | |
| [2025-01-07 20:39:40,505][00160] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3651.7). Total num frames: 2326528. Throughput: 0: 893.1. Samples: 580100. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-01-07 20:39:40,508][00160] Avg episode reward: [(0, '11.302')] | |
| [2025-01-07 20:39:41,624][03281] Updated weights for policy 0, policy_version 570 (0.0021) | |
| [2025-01-07 20:39:45,505][00160] Fps is (10 sec: 4097.7, 60 sec: 3754.7, 300 sec: 3665.6). Total num frames: 2351104. Throughput: 0: 914.8. Samples: 586756. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-07 20:39:45,507][00160] Avg episode reward: [(0, '11.106')] | |
| [2025-01-07 20:39:50,508][00160] Fps is (10 sec: 3685.3, 60 sec: 3618.0, 300 sec: 3665.5). Total num frames: 2363392. Throughput: 0: 930.0. Samples: 591950. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:39:50,511][00160] Avg episode reward: [(0, '10.247')] | |
| [2025-01-07 20:39:53,540][03281] Updated weights for policy 0, policy_version 580 (0.0028) | |
| [2025-01-07 20:39:55,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3618.2, 300 sec: 3651.7). Total num frames: 2383872. Throughput: 0: 905.0. Samples: 593966. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-01-07 20:39:55,508][00160] Avg episode reward: [(0, '11.290')] | |
| [2025-01-07 20:40:00,505][00160] Fps is (10 sec: 4097.2, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 2404352. Throughput: 0: 904.5. Samples: 600334. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-07 20:40:00,513][00160] Avg episode reward: [(0, '11.383')] | |
| [2025-01-07 20:40:02,799][03281] Updated weights for policy 0, policy_version 590 (0.0017) | |
| [2025-01-07 20:40:05,507][00160] Fps is (10 sec: 4095.3, 60 sec: 3754.6, 300 sec: 3679.4). Total num frames: 2424832. Throughput: 0: 947.2. Samples: 606304. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-01-07 20:40:05,512][00160] Avg episode reward: [(0, '11.463')] | |
| [2025-01-07 20:40:10,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 2437120. Throughput: 0: 922.6. Samples: 608228. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2025-01-07 20:40:10,508][00160] Avg episode reward: [(0, '13.122')] | |
| [2025-01-07 20:40:10,516][03268] Saving new best policy, reward=13.122! | |
| [2025-01-07 20:40:14,929][03281] Updated weights for policy 0, policy_version 600 (0.0034) | |
| [2025-01-07 20:40:15,505][00160] Fps is (10 sec: 3277.3, 60 sec: 3618.2, 300 sec: 3651.7). Total num frames: 2457600. Throughput: 0: 896.9. Samples: 613718. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-01-07 20:40:15,512][00160] Avg episode reward: [(0, '12.711')] | |
| [2025-01-07 20:40:20,505][00160] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3665.6). Total num frames: 2478080. Throughput: 0: 944.1. Samples: 620288. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-07 20:40:20,509][00160] Avg episode reward: [(0, '12.621')] | |
| [2025-01-07 20:40:20,521][03268] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000605_2478080.pth... | |
| [2025-01-07 20:40:20,682][03268] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000390_1597440.pth | |
| [2025-01-07 20:40:25,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 2490368. Throughput: 0: 938.4. Samples: 622326. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-01-07 20:40:25,512][00160] Avg episode reward: [(0, '12.943')] | |
| [2025-01-07 20:40:27,169][03281] Updated weights for policy 0, policy_version 610 (0.0020) | |
| [2025-01-07 20:40:30,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3651.7). Total num frames: 2510848. Throughput: 0: 894.3. Samples: 626998. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2025-01-07 20:40:30,512][00160] Avg episode reward: [(0, '12.105')] | |
| [2025-01-07 20:40:35,505][00160] Fps is (10 sec: 4096.0, 60 sec: 3686.6, 300 sec: 3651.7). Total num frames: 2531328. Throughput: 0: 926.2. Samples: 633628. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-07 20:40:35,512][00160] Avg episode reward: [(0, '12.075')] | |
| [2025-01-07 20:40:36,533][03281] Updated weights for policy 0, policy_version 620 (0.0027) | |
| [2025-01-07 20:40:40,505][00160] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 2547712. Throughput: 0: 945.8. Samples: 636528. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:40:40,510][00160] Avg episode reward: [(0, '12.322')] | |
| [2025-01-07 20:40:45,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 2564096. Throughput: 0: 892.5. Samples: 640498. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:40:45,508][00160] Avg episode reward: [(0, '12.988')] | |
| [2025-01-07 20:40:48,588][03281] Updated weights for policy 0, policy_version 630 (0.0014) | |
| [2025-01-07 20:40:50,505][00160] Fps is (10 sec: 3686.4, 60 sec: 3686.6, 300 sec: 3651.7). Total num frames: 2584576. Throughput: 0: 906.6. Samples: 647098. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-01-07 20:40:50,510][00160] Avg episode reward: [(0, '13.587')] | |
| [2025-01-07 20:40:50,564][03268] Saving new best policy, reward=13.587! | |
| [2025-01-07 20:40:55,505][00160] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 2605056. Throughput: 0: 934.4. Samples: 650276. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:40:55,511][00160] Avg episode reward: [(0, '13.386')] | |
| [2025-01-07 20:41:00,461][03281] Updated weights for policy 0, policy_version 640 (0.0040) | |
| [2025-01-07 20:41:00,505][00160] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 2621440. Throughput: 0: 908.1. Samples: 654584. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2025-01-07 20:41:00,510][00160] Avg episode reward: [(0, '12.843')] | |
| [2025-01-07 20:41:05,505][00160] Fps is (10 sec: 3686.4, 60 sec: 3618.2, 300 sec: 3651.7). Total num frames: 2641920. Throughput: 0: 894.5. Samples: 660540. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-01-07 20:41:05,513][00160] Avg episode reward: [(0, '12.972')] | |
| [2025-01-07 20:41:10,058][03281] Updated weights for policy 0, policy_version 650 (0.0014) | |
| [2025-01-07 20:41:10,507][00160] Fps is (10 sec: 4095.2, 60 sec: 3754.6, 300 sec: 3679.4). Total num frames: 2662400. Throughput: 0: 922.3. Samples: 663832. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2025-01-07 20:41:10,509][00160] Avg episode reward: [(0, '13.068')] | |
| [2025-01-07 20:41:15,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 2674688. Throughput: 0: 924.0. Samples: 668580. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2025-01-07 20:41:15,510][00160] Avg episode reward: [(0, '13.144')] | |
| [2025-01-07 20:41:20,505][00160] Fps is (10 sec: 3277.4, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 2695168. Throughput: 0: 895.3. Samples: 673918. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-01-07 20:41:20,508][00160] Avg episode reward: [(0, '12.678')] | |
| [2025-01-07 20:41:22,122][03281] Updated weights for policy 0, policy_version 660 (0.0023) | |
| [2025-01-07 20:41:25,505][00160] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3665.6). Total num frames: 2715648. Throughput: 0: 903.9. Samples: 677202. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-07 20:41:25,508][00160] Avg episode reward: [(0, '11.861')] | |
| [2025-01-07 20:41:30,512][00160] Fps is (10 sec: 3683.9, 60 sec: 3686.0, 300 sec: 3665.5). Total num frames: 2732032. Throughput: 0: 939.2. Samples: 682768. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:41:30,514][00160] Avg episode reward: [(0, '13.017')] | |
| [2025-01-07 20:41:34,091][03281] Updated weights for policy 0, policy_version 670 (0.0021) | |
| [2025-01-07 20:41:35,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 2748416. Throughput: 0: 894.8. Samples: 687362. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:41:35,508][00160] Avg episode reward: [(0, '13.530')] | |
| [2025-01-07 20:41:40,505][00160] Fps is (10 sec: 3688.9, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 2768896. Throughput: 0: 894.2. Samples: 690516. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:41:40,508][00160] Avg episode reward: [(0, '14.600')] | |
| [2025-01-07 20:41:40,516][03268] Saving new best policy, reward=14.600! | |
| [2025-01-07 20:41:44,138][03281] Updated weights for policy 0, policy_version 680 (0.0013) | |
| [2025-01-07 20:41:45,508][00160] Fps is (10 sec: 4094.8, 60 sec: 3754.5, 300 sec: 3679.4). Total num frames: 2789376. Throughput: 0: 937.7. Samples: 696784. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:41:45,513][00160] Avg episode reward: [(0, '15.064')] | |
| [2025-01-07 20:41:45,515][03268] Saving new best policy, reward=15.064! | |
| [2025-01-07 20:41:50,506][00160] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 2801664. Throughput: 0: 891.0. Samples: 700634. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:41:50,508][00160] Avg episode reward: [(0, '15.087')] | |
| [2025-01-07 20:41:50,520][03268] Saving new best policy, reward=15.087! | |
| [2025-01-07 20:41:55,505][00160] Fps is (10 sec: 3277.8, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 2822144. Throughput: 0: 885.9. Samples: 703694. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0) | |
| [2025-01-07 20:41:55,511][00160] Avg episode reward: [(0, '14.054')] | |
| [2025-01-07 20:41:55,814][03281] Updated weights for policy 0, policy_version 690 (0.0019) | |
| [2025-01-07 20:42:00,505][00160] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 2842624. Throughput: 0: 926.5. Samples: 710272. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:42:00,508][00160] Avg episode reward: [(0, '14.417')] | |
| [2025-01-07 20:42:05,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3651.7). Total num frames: 2854912. Throughput: 0: 905.5. Samples: 714664. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:42:05,508][00160] Avg episode reward: [(0, '14.254')] | |
| [2025-01-07 20:42:08,144][03281] Updated weights for policy 0, policy_version 700 (0.0022) | |
| [2025-01-07 20:42:10,506][00160] Fps is (10 sec: 3276.7, 60 sec: 3550.0, 300 sec: 3637.8). Total num frames: 2875392. Throughput: 0: 888.9. Samples: 717202. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-07 20:42:10,508][00160] Avg episode reward: [(0, '14.044')] | |
| [2025-01-07 20:42:15,505][00160] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 2895872. Throughput: 0: 906.6. Samples: 723558. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-07 20:42:15,507][00160] Avg episode reward: [(0, '14.542')] | |
| [2025-01-07 20:42:18,202][03281] Updated weights for policy 0, policy_version 710 (0.0015) | |
| [2025-01-07 20:42:20,505][00160] Fps is (10 sec: 3686.5, 60 sec: 3618.1, 300 sec: 3665.6). Total num frames: 2912256. Throughput: 0: 920.4. Samples: 728782. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-01-07 20:42:20,509][00160] Avg episode reward: [(0, '14.984')] | |
| [2025-01-07 20:42:20,519][03268] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000711_2912256.pth... | |
| [2025-01-07 20:42:20,647][03268] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000498_2039808.pth | |
| [2025-01-07 20:42:25,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 2928640. Throughput: 0: 893.3. Samples: 730714. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:42:25,510][00160] Avg episode reward: [(0, '15.350')] | |
| [2025-01-07 20:42:25,514][03268] Saving new best policy, reward=15.350! | |
| [2025-01-07 20:42:29,932][03281] Updated weights for policy 0, policy_version 720 (0.0027) | |
| [2025-01-07 20:42:30,509][00160] Fps is (10 sec: 3684.9, 60 sec: 3618.3, 300 sec: 3637.8). Total num frames: 2949120. Throughput: 0: 888.6. Samples: 736772. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-01-07 20:42:30,512][00160] Avg episode reward: [(0, '16.316')] | |
| [2025-01-07 20:42:30,526][03268] Saving new best policy, reward=16.316! | |
| [2025-01-07 20:42:35,505][00160] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 2965504. Throughput: 0: 927.3. Samples: 742364. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2025-01-07 20:42:35,511][00160] Avg episode reward: [(0, '18.308')] | |
| [2025-01-07 20:42:35,602][03268] Saving new best policy, reward=18.308! | |
| [2025-01-07 20:42:40,505][00160] Fps is (10 sec: 2868.4, 60 sec: 3481.6, 300 sec: 3623.9). Total num frames: 2977792. Throughput: 0: 897.1. Samples: 744062. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:42:40,513][00160] Avg episode reward: [(0, '18.012')] | |
| [2025-01-07 20:42:42,455][03281] Updated weights for policy 0, policy_version 730 (0.0029) | |
| [2025-01-07 20:42:45,505][00160] Fps is (10 sec: 3686.4, 60 sec: 3550.0, 300 sec: 3623.9). Total num frames: 3002368. Throughput: 0: 871.6. Samples: 749494. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:42:45,510][00160] Avg episode reward: [(0, '19.141')] | |
| [2025-01-07 20:42:45,515][03268] Saving new best policy, reward=19.141! | |
| [2025-01-07 20:42:50,505][00160] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 3018752. Throughput: 0: 910.7. Samples: 755644. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:42:50,513][00160] Avg episode reward: [(0, '19.230')] | |
| [2025-01-07 20:42:50,527][03268] Saving new best policy, reward=19.230! | |
| [2025-01-07 20:42:54,069][03281] Updated weights for policy 0, policy_version 740 (0.0024) | |
| [2025-01-07 20:42:55,505][00160] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3623.9). Total num frames: 3031040. Throughput: 0: 894.1. Samples: 757434. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-01-07 20:42:55,516][00160] Avg episode reward: [(0, '19.114')] | |
| [2025-01-07 20:43:00,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3610.0). Total num frames: 3051520. Throughput: 0: 862.7. Samples: 762380. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-01-07 20:43:00,510][00160] Avg episode reward: [(0, '18.208')] | |
| [2025-01-07 20:43:04,789][03281] Updated weights for policy 0, policy_version 750 (0.0025) | |
| [2025-01-07 20:43:05,505][00160] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 3072000. Throughput: 0: 886.0. Samples: 768654. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:43:05,508][00160] Avg episode reward: [(0, '18.802')] | |
| [2025-01-07 20:43:10,506][00160] Fps is (10 sec: 3686.3, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 3088384. Throughput: 0: 901.0. Samples: 771258. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:43:10,514][00160] Avg episode reward: [(0, '18.486')] | |
| [2025-01-07 20:43:15,506][00160] Fps is (10 sec: 3276.7, 60 sec: 3481.6, 300 sec: 3610.0). Total num frames: 3104768. Throughput: 0: 858.3. Samples: 775394. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-07 20:43:15,508][00160] Avg episode reward: [(0, '18.216')] | |
| [2025-01-07 20:43:17,179][03281] Updated weights for policy 0, policy_version 760 (0.0028) | |
| [2025-01-07 20:43:20,505][00160] Fps is (10 sec: 3686.5, 60 sec: 3549.9, 300 sec: 3623.9). Total num frames: 3125248. Throughput: 0: 875.9. Samples: 781780. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:43:20,508][00160] Avg episode reward: [(0, '18.359')] | |
| [2025-01-07 20:43:25,507][00160] Fps is (10 sec: 3685.8, 60 sec: 3549.7, 300 sec: 3637.8). Total num frames: 3141632. Throughput: 0: 908.1. Samples: 784928. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-07 20:43:25,516][00160] Avg episode reward: [(0, '17.737')] | |
| [2025-01-07 20:43:29,092][03281] Updated weights for policy 0, policy_version 770 (0.0030) | |
| [2025-01-07 20:43:30,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3481.8, 300 sec: 3610.0). Total num frames: 3158016. Throughput: 0: 874.2. Samples: 788834. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:43:30,508][00160] Avg episode reward: [(0, '17.177')] | |
| [2025-01-07 20:43:35,505][00160] Fps is (10 sec: 3687.1, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 3178496. Throughput: 0: 871.8. Samples: 794874. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2025-01-07 20:43:35,508][00160] Avg episode reward: [(0, '17.254')] | |
| [2025-01-07 20:43:39,063][03281] Updated weights for policy 0, policy_version 780 (0.0023) | |
| [2025-01-07 20:43:40,512][00160] Fps is (10 sec: 4093.5, 60 sec: 3686.0, 300 sec: 3637.7). Total num frames: 3198976. Throughput: 0: 902.6. Samples: 798058. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:43:40,518][00160] Avg episode reward: [(0, '17.375')] | |
| [2025-01-07 20:43:45,506][00160] Fps is (10 sec: 3276.7, 60 sec: 3481.6, 300 sec: 3610.0). Total num frames: 3211264. Throughput: 0: 890.0. Samples: 802432. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2025-01-07 20:43:45,507][00160] Avg episode reward: [(0, '17.608')] | |
| [2025-01-07 20:43:50,505][00160] Fps is (10 sec: 2869.0, 60 sec: 3481.6, 300 sec: 3596.2). Total num frames: 3227648. Throughput: 0: 869.6. Samples: 807786. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:43:50,509][00160] Avg episode reward: [(0, '18.293')] | |
| [2025-01-07 20:43:51,581][03281] Updated weights for policy 0, policy_version 790 (0.0024) | |
| [2025-01-07 20:43:55,505][00160] Fps is (10 sec: 3686.5, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 3248128. Throughput: 0: 880.5. Samples: 810878. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-01-07 20:43:55,509][00160] Avg episode reward: [(0, '18.476')] | |
| [2025-01-07 20:44:00,505][00160] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 3264512. Throughput: 0: 905.4. Samples: 816138. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-07 20:44:00,508][00160] Avg episode reward: [(0, '18.130')] | |
| [2025-01-07 20:44:03,919][03281] Updated weights for policy 0, policy_version 800 (0.0017) | |
| [2025-01-07 20:44:05,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3596.1). Total num frames: 3280896. Throughput: 0: 865.8. Samples: 820742. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:44:05,510][00160] Avg episode reward: [(0, '17.635')] | |
| [2025-01-07 20:44:10,505][00160] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3596.2). Total num frames: 3301376. Throughput: 0: 866.5. Samples: 823918. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-07 20:44:10,509][00160] Avg episode reward: [(0, '17.443')] | |
| [2025-01-07 20:44:14,030][03281] Updated weights for policy 0, policy_version 810 (0.0019) | |
| [2025-01-07 20:44:15,509][00160] Fps is (10 sec: 4094.4, 60 sec: 3617.9, 300 sec: 3623.9). Total num frames: 3321856. Throughput: 0: 910.0. Samples: 829786. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:44:15,512][00160] Avg episode reward: [(0, '17.592')] | |
| [2025-01-07 20:44:20,511][00160] Fps is (10 sec: 3274.8, 60 sec: 3481.2, 300 sec: 3596.1). Total num frames: 3334144. Throughput: 0: 866.0. Samples: 833850. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-01-07 20:44:20,517][00160] Avg episode reward: [(0, '17.780')] | |
| [2025-01-07 20:44:20,533][03268] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000814_3334144.pth... | |
| [2025-01-07 20:44:20,676][03268] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000605_2478080.pth | |
| [2025-01-07 20:44:25,505][00160] Fps is (10 sec: 3278.1, 60 sec: 3550.0, 300 sec: 3582.3). Total num frames: 3354624. Throughput: 0: 864.1. Samples: 836938. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2025-01-07 20:44:25,508][00160] Avg episode reward: [(0, '17.950')] | |
| [2025-01-07 20:44:26,087][03281] Updated weights for policy 0, policy_version 820 (0.0019) | |
| [2025-01-07 20:44:30,508][00160] Fps is (10 sec: 4097.5, 60 sec: 3618.0, 300 sec: 3610.1). Total num frames: 3375104. Throughput: 0: 905.1. Samples: 843164. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:44:30,512][00160] Avg episode reward: [(0, '18.031')] | |
| [2025-01-07 20:44:35,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3596.2). Total num frames: 3387392. Throughput: 0: 875.0. Samples: 847162. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:44:35,507][00160] Avg episode reward: [(0, '17.834')] | |
| [2025-01-07 20:44:38,397][03281] Updated weights for policy 0, policy_version 830 (0.0026) | |
| [2025-01-07 20:44:40,505][00160] Fps is (10 sec: 3277.6, 60 sec: 3482.0, 300 sec: 3582.3). Total num frames: 3407872. Throughput: 0: 870.1. Samples: 850032. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-01-07 20:44:40,511][00160] Avg episode reward: [(0, '18.447')] | |
| [2025-01-07 20:44:45,505][00160] Fps is (10 sec: 4096.0, 60 sec: 3618.2, 300 sec: 3610.1). Total num frames: 3428352. Throughput: 0: 887.9. Samples: 856094. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:44:45,513][00160] Avg episode reward: [(0, '19.874')] | |
| [2025-01-07 20:44:45,516][03268] Saving new best policy, reward=19.874! | |
| [2025-01-07 20:44:49,793][03281] Updated weights for policy 0, policy_version 840 (0.0026) | |
| [2025-01-07 20:44:50,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 3440640. Throughput: 0: 885.4. Samples: 860584. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:44:50,508][00160] Avg episode reward: [(0, '19.258')] | |
| [2025-01-07 20:44:55,505][00160] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3568.4). Total num frames: 3457024. Throughput: 0: 863.4. Samples: 862772. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-07 20:44:55,511][00160] Avg episode reward: [(0, '19.501')] | |
| [2025-01-07 20:45:00,505][00160] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3568.4). Total num frames: 3477504. Throughput: 0: 873.8. Samples: 869102. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:45:00,507][00160] Avg episode reward: [(0, '20.199')] | |
| [2025-01-07 20:45:00,522][03268] Saving new best policy, reward=20.199! | |
| [2025-01-07 20:45:00,761][03281] Updated weights for policy 0, policy_version 850 (0.0018) | |
| [2025-01-07 20:45:05,505][00160] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 3493888. Throughput: 0: 895.4. Samples: 874138. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:45:05,511][00160] Avg episode reward: [(0, '19.371')] | |
| [2025-01-07 20:45:10,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3568.4). Total num frames: 3510272. Throughput: 0: 868.0. Samples: 876000. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:45:10,508][00160] Avg episode reward: [(0, '19.426')] | |
| [2025-01-07 20:45:13,218][03281] Updated weights for policy 0, policy_version 860 (0.0029) | |
| [2025-01-07 20:45:15,505][00160] Fps is (10 sec: 3686.4, 60 sec: 3481.8, 300 sec: 3568.4). Total num frames: 3530752. Throughput: 0: 860.0. Samples: 881864. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:45:15,511][00160] Avg episode reward: [(0, '19.857')] | |
| [2025-01-07 20:45:20,505][00160] Fps is (10 sec: 3686.4, 60 sec: 3550.2, 300 sec: 3582.3). Total num frames: 3547136. Throughput: 0: 900.7. Samples: 887694. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-07 20:45:20,508][00160] Avg episode reward: [(0, '19.490')] | |
| [2025-01-07 20:45:25,489][03281] Updated weights for policy 0, policy_version 870 (0.0030) | |
| [2025-01-07 20:45:25,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3568.4). Total num frames: 3563520. Throughput: 0: 877.8. Samples: 889534. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:45:25,508][00160] Avg episode reward: [(0, '18.961')] | |
| [2025-01-07 20:45:30,505][00160] Fps is (10 sec: 3686.4, 60 sec: 3481.7, 300 sec: 3568.4). Total num frames: 3584000. Throughput: 0: 863.2. Samples: 894938. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-07 20:45:30,510][00160] Avg episode reward: [(0, '18.807')] | |
| [2025-01-07 20:45:35,239][03281] Updated weights for policy 0, policy_version 880 (0.0022) | |
| [2025-01-07 20:45:35,507][00160] Fps is (10 sec: 4095.4, 60 sec: 3618.0, 300 sec: 3582.2). Total num frames: 3604480. Throughput: 0: 904.1. Samples: 901268. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:45:35,513][00160] Avg episode reward: [(0, '18.749')] | |
| [2025-01-07 20:45:40,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3568.4). Total num frames: 3616768. Throughput: 0: 900.9. Samples: 903314. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:45:40,511][00160] Avg episode reward: [(0, '19.132')] | |
| [2025-01-07 20:45:45,506][00160] Fps is (10 sec: 2867.6, 60 sec: 3413.3, 300 sec: 3554.5). Total num frames: 3633152. Throughput: 0: 860.8. Samples: 907836. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-07 20:45:45,512][00160] Avg episode reward: [(0, '18.629')] | |
| [2025-01-07 20:45:47,658][03281] Updated weights for policy 0, policy_version 890 (0.0021) | |
| [2025-01-07 20:45:50,505][00160] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3554.5). Total num frames: 3653632. Throughput: 0: 889.4. Samples: 914162. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:45:50,512][00160] Avg episode reward: [(0, '19.507')] | |
| [2025-01-07 20:45:55,505][00160] Fps is (10 sec: 3686.5, 60 sec: 3549.9, 300 sec: 3554.5). Total num frames: 3670016. Throughput: 0: 908.0. Samples: 916862. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-01-07 20:45:55,511][00160] Avg episode reward: [(0, '18.314')] | |
| [2025-01-07 20:46:00,217][03281] Updated weights for policy 0, policy_version 900 (0.0024) | |
| [2025-01-07 20:46:00,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3540.6). Total num frames: 3686400. Throughput: 0: 865.7. Samples: 920822. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-07 20:46:00,511][00160] Avg episode reward: [(0, '18.075')] | |
| [2025-01-07 20:46:05,505][00160] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3540.6). Total num frames: 3706880. Throughput: 0: 875.4. Samples: 927086. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:46:05,509][00160] Avg episode reward: [(0, '17.500')] | |
| [2025-01-07 20:46:10,505][00160] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3554.5). Total num frames: 3723264. Throughput: 0: 903.7. Samples: 930202. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:46:10,509][00160] Avg episode reward: [(0, '17.938')] | |
| [2025-01-07 20:46:11,331][03281] Updated weights for policy 0, policy_version 910 (0.0023) | |
| [2025-01-07 20:46:15,505][00160] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3526.7). Total num frames: 3735552. Throughput: 0: 871.4. Samples: 934150. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-01-07 20:46:15,507][00160] Avg episode reward: [(0, '17.806')] | |
| [2025-01-07 20:46:20,505][00160] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3540.6). Total num frames: 3760128. Throughput: 0: 858.4. Samples: 939896. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:46:20,511][00160] Avg episode reward: [(0, '19.071')] | |
| [2025-01-07 20:46:20,523][03268] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000918_3760128.pth... | |
| [2025-01-07 20:46:20,624][03268] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000711_2912256.pth | |
| [2025-01-07 20:46:22,559][03281] Updated weights for policy 0, policy_version 920 (0.0017) | |
| [2025-01-07 20:46:25,505][00160] Fps is (10 sec: 4505.6, 60 sec: 3618.1, 300 sec: 3554.6). Total num frames: 3780608. Throughput: 0: 881.3. Samples: 942972. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-07 20:46:25,510][00160] Avg episode reward: [(0, '19.693')] | |
| [2025-01-07 20:46:30,507][00160] Fps is (10 sec: 3276.3, 60 sec: 3481.5, 300 sec: 3540.6). Total num frames: 3792896. Throughput: 0: 886.9. Samples: 947746. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:46:30,510][00160] Avg episode reward: [(0, '19.677')] | |
| [2025-01-07 20:46:34,792][03281] Updated weights for policy 0, policy_version 930 (0.0019) | |
| [2025-01-07 20:46:35,505][00160] Fps is (10 sec: 2867.2, 60 sec: 3413.4, 300 sec: 3526.7). Total num frames: 3809280. Throughput: 0: 857.6. Samples: 952754. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-07 20:46:35,511][00160] Avg episode reward: [(0, '19.670')] | |
| [2025-01-07 20:46:40,506][00160] Fps is (10 sec: 3686.7, 60 sec: 3549.8, 300 sec: 3526.8). Total num frames: 3829760. Throughput: 0: 868.0. Samples: 955922. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:46:40,513][00160] Avg episode reward: [(0, '20.128')] | |
| [2025-01-07 20:46:45,509][00160] Fps is (10 sec: 3685.1, 60 sec: 3549.7, 300 sec: 3540.6). Total num frames: 3846144. Throughput: 0: 901.3. Samples: 961384. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:46:45,511][00160] Avg episode reward: [(0, '18.786')] | |
| [2025-01-07 20:46:46,297][03281] Updated weights for policy 0, policy_version 940 (0.0026) | |
| [2025-01-07 20:46:50,505][00160] Fps is (10 sec: 3277.0, 60 sec: 3481.6, 300 sec: 3526.7). Total num frames: 3862528. Throughput: 0: 856.1. Samples: 965612. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2025-01-07 20:46:50,507][00160] Avg episode reward: [(0, '18.188')] | |
| [2025-01-07 20:46:55,505][00160] Fps is (10 sec: 3687.7, 60 sec: 3549.9, 300 sec: 3526.7). Total num frames: 3883008. Throughput: 0: 856.3. Samples: 968734. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-07 20:46:55,508][00160] Avg episode reward: [(0, '17.747')] | |
| [2025-01-07 20:46:57,299][03281] Updated weights for policy 0, policy_version 950 (0.0021) | |
| [2025-01-07 20:47:00,507][00160] Fps is (10 sec: 3685.6, 60 sec: 3549.7, 300 sec: 3540.6). Total num frames: 3899392. Throughput: 0: 908.4. Samples: 975032. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:47:00,510][00160] Avg episode reward: [(0, '16.998')] | |
| [2025-01-07 20:47:05,507][00160] Fps is (10 sec: 2866.6, 60 sec: 3413.2, 300 sec: 3512.8). Total num frames: 3911680. Throughput: 0: 866.0. Samples: 978868. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:47:05,514][00160] Avg episode reward: [(0, '16.635')] | |
| [2025-01-07 20:47:09,687][03281] Updated weights for policy 0, policy_version 960 (0.0018) | |
| [2025-01-07 20:47:10,505][00160] Fps is (10 sec: 3277.5, 60 sec: 3481.6, 300 sec: 3512.8). Total num frames: 3932160. Throughput: 0: 858.8. Samples: 981618. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-07 20:47:10,508][00160] Avg episode reward: [(0, '17.723')] | |
| [2025-01-07 20:47:15,505][00160] Fps is (10 sec: 4096.8, 60 sec: 3618.1, 300 sec: 3526.7). Total num frames: 3952640. Throughput: 0: 892.3. Samples: 987896. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:47:15,509][00160] Avg episode reward: [(0, '17.999')] | |
| [2025-01-07 20:47:20,505][00160] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3526.7). Total num frames: 3969024. Throughput: 0: 882.0. Samples: 992446. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-07 20:47:20,507][00160] Avg episode reward: [(0, '18.543')] | |
| [2025-01-07 20:47:21,994][03281] Updated weights for policy 0, policy_version 970 (0.0013) | |
| [2025-01-07 20:47:25,505][00160] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3512.9). Total num frames: 3985408. Throughput: 0: 859.6. Samples: 994602. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-07 20:47:25,513][00160] Avg episode reward: [(0, '19.035')] | |
| [2025-01-07 20:47:29,852][03268] Stopping Batcher_0... | |
| [2025-01-07 20:47:29,853][03268] Loop batcher_evt_loop terminating... | |
| [2025-01-07 20:47:29,854][00160] Component Batcher_0 stopped! | |
| [2025-01-07 20:47:29,861][03268] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2025-01-07 20:47:29,864][00160] Component RolloutWorker_w0 process died already! Don't wait for it. | |
| [2025-01-07 20:47:29,939][03281] Weights refcount: 2 0 | |
| [2025-01-07 20:47:29,943][00160] Component InferenceWorker_p0-w0 stopped! | |
| [2025-01-07 20:47:29,949][03281] Stopping InferenceWorker_p0-w0... | |
| [2025-01-07 20:47:29,949][03281] Loop inference_proc0-0_evt_loop terminating... | |
| [2025-01-07 20:47:29,997][03268] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000814_3334144.pth | |
| [2025-01-07 20:47:30,010][03268] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2025-01-07 20:47:30,162][03268] Stopping LearnerWorker_p0... | |
| [2025-01-07 20:47:30,163][00160] Component LearnerWorker_p0 stopped! | |
| [2025-01-07 20:47:30,164][03268] Loop learner_proc0_evt_loop terminating... | |
| [2025-01-07 20:47:30,274][00160] Component RolloutWorker_w1 stopped! | |
| [2025-01-07 20:47:30,279][03282] Stopping RolloutWorker_w1... | |
| [2025-01-07 20:47:30,280][03282] Loop rollout_proc1_evt_loop terminating... | |
| [2025-01-07 20:47:30,286][00160] Component RolloutWorker_w5 stopped! | |
| [2025-01-07 20:47:30,292][03287] Stopping RolloutWorker_w5... | |
| [2025-01-07 20:47:30,296][03287] Loop rollout_proc5_evt_loop terminating... | |
| [2025-01-07 20:47:30,311][00160] Component RolloutWorker_w7 stopped! | |
| [2025-01-07 20:47:30,318][03289] Stopping RolloutWorker_w7... | |
| [2025-01-07 20:47:30,318][03289] Loop rollout_proc7_evt_loop terminating... | |
| [2025-01-07 20:47:30,326][00160] Component RolloutWorker_w3 stopped! | |
| [2025-01-07 20:47:30,333][03285] Stopping RolloutWorker_w3... | |
| [2025-01-07 20:47:30,338][03285] Loop rollout_proc3_evt_loop terminating... | |
| [2025-01-07 20:47:30,390][00160] Component RolloutWorker_w2 stopped! | |
| [2025-01-07 20:47:30,390][03284] Stopping RolloutWorker_w2... | |
| [2025-01-07 20:47:30,393][03284] Loop rollout_proc2_evt_loop terminating... | |
| [2025-01-07 20:47:30,443][03286] Stopping RolloutWorker_w4... | |
| [2025-01-07 20:47:30,442][00160] Component RolloutWorker_w4 stopped! | |
| [2025-01-07 20:47:30,444][03286] Loop rollout_proc4_evt_loop terminating... | |
| [2025-01-07 20:47:30,454][00160] Component RolloutWorker_w6 stopped! | |
| [2025-01-07 20:47:30,455][03288] Stopping RolloutWorker_w6... | |
| [2025-01-07 20:47:30,456][00160] Waiting for process learner_proc0 to stop... | |
| [2025-01-07 20:47:30,459][03288] Loop rollout_proc6_evt_loop terminating... | |
| [2025-01-07 20:47:31,845][00160] Waiting for process inference_proc0-0 to join... | |
| [2025-01-07 20:47:31,854][00160] Waiting for process rollout_proc0 to join... | |
| [2025-01-07 20:47:31,859][00160] Waiting for process rollout_proc1 to join... | |
| [2025-01-07 20:47:34,312][00160] Waiting for process rollout_proc2 to join... | |
| [2025-01-07 20:47:34,507][00160] Waiting for process rollout_proc3 to join... | |
| [2025-01-07 20:47:34,511][00160] Waiting for process rollout_proc4 to join... | |
| [2025-01-07 20:47:34,514][00160] Waiting for process rollout_proc5 to join... | |
| [2025-01-07 20:47:34,518][00160] Waiting for process rollout_proc6 to join... | |
| [2025-01-07 20:47:34,525][00160] Waiting for process rollout_proc7 to join... | |
| [2025-01-07 20:47:34,530][00160] Batcher 0 profile tree view: | |
| batching: 24.5566, releasing_batches: 0.0350 | |
| [2025-01-07 20:47:34,532][00160] InferenceWorker_p0-w0 profile tree view: | |
| wait_policy: 0.0125 | |
| wait_policy_total: 464.6979 | |
| update_model: 9.2147 | |
| weight_update: 0.0017 | |
| one_step: 0.0063 | |
| handle_policy_step: 600.2092 | |
| deserialize: 15.5634, stack: 3.3464, obs_to_device_normalize: 128.4312, forward: 308.7785, send_messages: 26.7435 | |
| prepare_outputs: 87.3106 | |
| to_cpu: 52.8923 | |
| [2025-01-07 20:47:34,535][00160] Learner 0 profile tree view: | |
| misc: 0.0050, prepare_batch: 13.6580 | |
| train: 72.7932 | |
| epoch_init: 0.0062, minibatch_init: 0.0089, losses_postprocess: 0.6124, kl_divergence: 0.6103, after_optimizer: 33.4166 | |
| calculate_losses: 25.9801 | |
| losses_init: 0.0067, forward_head: 1.1911, bptt_initial: 17.6358, tail: 1.1172, advantages_returns: 0.2796, losses: 3.6176 | |
| bptt: 1.8219 | |
| bptt_forward_core: 1.7258 | |
| update: 11.5400 | |
| clip: 0.8921 | |
| [2025-01-07 20:47:34,537][00160] RolloutWorker_w7 profile tree view: | |
| wait_for_trajectories: 0.3595, enqueue_policy_requests: 111.9042, env_step: 875.8608, overhead: 16.3389, complete_rollouts: 8.5513 | |
| save_policy_outputs: 24.9170 | |
| split_output_tensors: 9.9875 | |
| [2025-01-07 20:47:34,539][00160] Loop Runner_EvtLoop terminating... | |
| [2025-01-07 20:47:34,541][00160] Runner profile tree view: | |
| main_loop: 1148.1188 | |
| [2025-01-07 20:47:34,542][00160] Collected {0: 4005888}, FPS: 3489.1 | |
| [2025-01-07 20:48:56,262][00160] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2025-01-07 20:48:56,264][00160] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2025-01-07 20:48:56,266][00160] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2025-01-07 20:48:56,268][00160] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2025-01-07 20:48:56,271][00160] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2025-01-07 20:48:56,273][00160] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2025-01-07 20:48:56,274][00160] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! | |
| [2025-01-07 20:48:56,276][00160] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2025-01-07 20:48:56,277][00160] Adding new argument 'push_to_hub'=False that is not in the saved config file! | |
| [2025-01-07 20:48:56,278][00160] Adding new argument 'hf_repository'=None that is not in the saved config file! | |
| [2025-01-07 20:48:56,279][00160] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2025-01-07 20:48:56,280][00160] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2025-01-07 20:48:56,281][00160] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2025-01-07 20:48:56,282][00160] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2025-01-07 20:48:56,283][00160] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2025-01-07 20:48:56,318][00160] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-01-07 20:48:56,323][00160] RunningMeanStd input shape: (3, 72, 128) | |
| [2025-01-07 20:48:56,326][00160] RunningMeanStd input shape: (1,) | |
| [2025-01-07 20:48:56,340][00160] ConvEncoder: input_channels=3 | |
| [2025-01-07 20:48:56,445][00160] Conv encoder output size: 512 | |
| [2025-01-07 20:48:56,447][00160] Policy head output size: 512 | |
| [2025-01-07 20:48:56,724][00160] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2025-01-07 20:48:57,553][00160] Num frames 100... | |
| [2025-01-07 20:48:57,692][00160] Num frames 200... | |
| [2025-01-07 20:48:57,827][00160] Num frames 300... | |
| [2025-01-07 20:48:57,959][00160] Num frames 400... | |
| [2025-01-07 20:48:58,090][00160] Num frames 500... | |
| [2025-01-07 20:48:58,230][00160] Num frames 600... | |
| [2025-01-07 20:48:58,359][00160] Num frames 700... | |
| [2025-01-07 20:48:58,489][00160] Num frames 800... | |
| [2025-01-07 20:48:58,615][00160] Num frames 900... | |
| [2025-01-07 20:48:58,753][00160] Num frames 1000... | |
| [2025-01-07 20:48:58,884][00160] Num frames 1100... | |
| [2025-01-07 20:48:59,014][00160] Num frames 1200... | |
| [2025-01-07 20:48:59,095][00160] Avg episode rewards: #0: 25.180, true rewards: #0: 12.180 | |
| [2025-01-07 20:48:59,096][00160] Avg episode reward: 25.180, avg true_objective: 12.180 | |
| [2025-01-07 20:48:59,207][00160] Num frames 1300... | |
| [2025-01-07 20:48:59,336][00160] Num frames 1400... | |
| [2025-01-07 20:48:59,459][00160] Num frames 1500... | |
| [2025-01-07 20:48:59,577][00160] Avg episode rewards: #0: 15.235, true rewards: #0: 7.735 | |
| [2025-01-07 20:48:59,580][00160] Avg episode reward: 15.235, avg true_objective: 7.735 | |
| [2025-01-07 20:48:59,653][00160] Num frames 1600... | |
| [2025-01-07 20:48:59,788][00160] Num frames 1700... | |
| [2025-01-07 20:48:59,916][00160] Num frames 1800... | |
| [2025-01-07 20:49:00,044][00160] Num frames 1900... | |
| [2025-01-07 20:49:00,171][00160] Num frames 2000... | |
| [2025-01-07 20:49:00,306][00160] Num frames 2100... | |
| [2025-01-07 20:49:00,435][00160] Num frames 2200... | |
| [2025-01-07 20:49:00,560][00160] Num frames 2300... | |
| [2025-01-07 20:49:00,687][00160] Num frames 2400... | |
| [2025-01-07 20:49:00,759][00160] Avg episode rewards: #0: 16.037, true rewards: #0: 8.037 | |
| [2025-01-07 20:49:00,761][00160] Avg episode reward: 16.037, avg true_objective: 8.037 | |
| [2025-01-07 20:49:00,877][00160] Num frames 2500... | |
| [2025-01-07 20:49:01,016][00160] Num frames 2600... | |
| [2025-01-07 20:49:01,142][00160] Num frames 2700... | |
| [2025-01-07 20:49:01,273][00160] Num frames 2800... | |
| [2025-01-07 20:49:01,395][00160] Num frames 2900... | |
| [2025-01-07 20:49:01,523][00160] Num frames 3000... | |
| [2025-01-07 20:49:01,649][00160] Num frames 3100... | |
| [2025-01-07 20:49:01,728][00160] Avg episode rewards: #0: 14.788, true rewards: #0: 7.787 | |
| [2025-01-07 20:49:01,731][00160] Avg episode reward: 14.788, avg true_objective: 7.787 | |
| [2025-01-07 20:49:01,845][00160] Num frames 3200... | |
| [2025-01-07 20:49:01,966][00160] Num frames 3300... | |
| [2025-01-07 20:49:02,091][00160] Num frames 3400... | |
| [2025-01-07 20:49:02,223][00160] Num frames 3500... | |
| [2025-01-07 20:49:02,350][00160] Num frames 3600... | |
| [2025-01-07 20:49:02,473][00160] Num frames 3700... | |
| [2025-01-07 20:49:02,594][00160] Num frames 3800... | |
| [2025-01-07 20:49:02,752][00160] Avg episode rewards: #0: 15.166, true rewards: #0: 7.766 | |
| [2025-01-07 20:49:02,754][00160] Avg episode reward: 15.166, avg true_objective: 7.766 | |
| [2025-01-07 20:49:02,783][00160] Num frames 3900... | |
| [2025-01-07 20:49:02,905][00160] Num frames 4000... | |
| [2025-01-07 20:49:03,028][00160] Num frames 4100... | |
| [2025-01-07 20:49:03,151][00160] Num frames 4200... | |
| [2025-01-07 20:49:03,288][00160] Num frames 4300... | |
| [2025-01-07 20:49:03,413][00160] Num frames 4400... | |
| [2025-01-07 20:49:03,536][00160] Num frames 4500... | |
| [2025-01-07 20:49:03,664][00160] Num frames 4600... | |
| [2025-01-07 20:49:03,823][00160] Avg episode rewards: #0: 15.472, true rewards: #0: 7.805 | |
| [2025-01-07 20:49:03,825][00160] Avg episode reward: 15.472, avg true_objective: 7.805 | |
| [2025-01-07 20:49:03,851][00160] Num frames 4700... | |
| [2025-01-07 20:49:03,976][00160] Num frames 4800... | |
| [2025-01-07 20:49:04,104][00160] Num frames 4900... | |
| [2025-01-07 20:49:04,237][00160] Num frames 5000... | |
| [2025-01-07 20:49:04,365][00160] Num frames 5100... | |
| [2025-01-07 20:49:04,490][00160] Num frames 5200... | |
| [2025-01-07 20:49:04,613][00160] Num frames 5300... | |
| [2025-01-07 20:49:04,742][00160] Num frames 5400... | |
| [2025-01-07 20:49:04,874][00160] Num frames 5500... | |
| [2025-01-07 20:49:04,997][00160] Num frames 5600... | |
| [2025-01-07 20:49:05,073][00160] Avg episode rewards: #0: 15.730, true rewards: #0: 8.016 | |
| [2025-01-07 20:49:05,075][00160] Avg episode reward: 15.730, avg true_objective: 8.016 | |
| [2025-01-07 20:49:05,197][00160] Num frames 5700... | |
| [2025-01-07 20:49:05,328][00160] Num frames 5800... | |
| [2025-01-07 20:49:05,452][00160] Num frames 5900... | |
| [2025-01-07 20:49:05,577][00160] Num frames 6000... | |
| [2025-01-07 20:49:05,702][00160] Num frames 6100... | |
| [2025-01-07 20:49:05,842][00160] Num frames 6200... | |
| [2025-01-07 20:49:06,003][00160] Num frames 6300... | |
| [2025-01-07 20:49:06,177][00160] Num frames 6400... | |
| [2025-01-07 20:49:06,348][00160] Num frames 6500... | |
| [2025-01-07 20:49:06,515][00160] Num frames 6600... | |
| [2025-01-07 20:49:06,687][00160] Num frames 6700... | |
| [2025-01-07 20:49:06,909][00160] Avg episode rewards: #0: 16.869, true rewards: #0: 8.494 | |
| [2025-01-07 20:49:06,911][00160] Avg episode reward: 16.869, avg true_objective: 8.494 | |
| [2025-01-07 20:49:06,924][00160] Num frames 6800... | |
| [2025-01-07 20:49:07,090][00160] Num frames 6900... | |
| [2025-01-07 20:49:07,269][00160] Num frames 7000... | |
| [2025-01-07 20:49:07,448][00160] Num frames 7100... | |
| [2025-01-07 20:49:07,595][00160] Avg episode rewards: #0: 15.497, true rewards: #0: 7.941 | |
| [2025-01-07 20:49:07,598][00160] Avg episode reward: 15.497, avg true_objective: 7.941 | |
| [2025-01-07 20:49:07,694][00160] Num frames 7200... | |
| [2025-01-07 20:49:07,881][00160] Num frames 7300... | |
| [2025-01-07 20:49:08,076][00160] Num frames 7400... | |
| [2025-01-07 20:49:08,277][00160] Num frames 7500... | |
| [2025-01-07 20:49:08,466][00160] Num frames 7600... | |
| [2025-01-07 20:49:08,618][00160] Num frames 7700... | |
| [2025-01-07 20:49:08,751][00160] Num frames 7800... | |
| [2025-01-07 20:49:08,880][00160] Num frames 7900... | |
| [2025-01-07 20:49:09,018][00160] Num frames 8000... | |
| [2025-01-07 20:49:09,188][00160] Avg episode rewards: #0: 15.988, true rewards: #0: 8.088 | |
| [2025-01-07 20:49:09,191][00160] Avg episode reward: 15.988, avg true_objective: 8.088 | |
| [2025-01-07 20:49:57,044][00160] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |
| [2025-01-07 20:51:11,514][00160] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2025-01-07 20:51:11,515][00160] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2025-01-07 20:51:11,517][00160] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2025-01-07 20:51:11,519][00160] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2025-01-07 20:51:11,521][00160] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2025-01-07 20:51:11,522][00160] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2025-01-07 20:51:11,524][00160] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! | |
| [2025-01-07 20:51:11,526][00160] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2025-01-07 20:51:11,527][00160] Adding new argument 'push_to_hub'=True that is not in the saved config file! | |
| [2025-01-07 20:51:11,530][00160] Adding new argument 'hf_repository'='ThomasSimonini/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! | |
| [2025-01-07 20:51:11,531][00160] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2025-01-07 20:51:11,532][00160] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2025-01-07 20:51:11,535][00160] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2025-01-07 20:51:11,536][00160] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2025-01-07 20:51:11,538][00160] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2025-01-07 20:51:11,567][00160] RunningMeanStd input shape: (3, 72, 128) | |
| [2025-01-07 20:51:11,568][00160] RunningMeanStd input shape: (1,) | |
| [2025-01-07 20:51:11,581][00160] ConvEncoder: input_channels=3 | |
| [2025-01-07 20:51:11,620][00160] Conv encoder output size: 512 | |
| [2025-01-07 20:51:11,623][00160] Policy head output size: 512 | |
| [2025-01-07 20:51:11,642][00160] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2025-01-07 20:51:12,075][00160] Num frames 100... | |
| [2025-01-07 20:51:12,215][00160] Num frames 200... | |
| [2025-01-07 20:51:12,368][00160] Num frames 300... | |
| [2025-01-07 20:51:12,497][00160] Num frames 400... | |
| [2025-01-07 20:51:12,627][00160] Num frames 500... | |
| [2025-01-07 20:51:12,754][00160] Num frames 600... | |
| [2025-01-07 20:51:12,883][00160] Num frames 700... | |
| [2025-01-07 20:51:13,007][00160] Num frames 800... | |
| [2025-01-07 20:51:13,130][00160] Num frames 900... | |
| [2025-01-07 20:51:13,201][00160] Avg episode rewards: #0: 18.120, true rewards: #0: 9.120 | |
| [2025-01-07 20:51:13,205][00160] Avg episode reward: 18.120, avg true_objective: 9.120 | |
| [2025-01-07 20:51:13,369][00160] Num frames 1000... | |
| [2025-01-07 20:51:13,494][00160] Num frames 1100... | |
| [2025-01-07 20:51:13,617][00160] Num frames 1200... | |
| [2025-01-07 20:51:13,743][00160] Num frames 1300... | |
| [2025-01-07 20:51:13,868][00160] Num frames 1400... | |
| [2025-01-07 20:51:13,996][00160] Num frames 1500... | |
| [2025-01-07 20:51:14,121][00160] Num frames 1600... | |
| [2025-01-07 20:51:14,255][00160] Num frames 1700... | |
| [2025-01-07 20:51:14,392][00160] Num frames 1800... | |
| [2025-01-07 20:51:14,521][00160] Num frames 1900... | |
| [2025-01-07 20:51:14,644][00160] Num frames 2000... | |
| [2025-01-07 20:51:14,771][00160] Num frames 2100... | |
| [2025-01-07 20:51:14,899][00160] Num frames 2200... | |
| [2025-01-07 20:51:15,024][00160] Num frames 2300... | |
| [2025-01-07 20:51:15,151][00160] Num frames 2400... | |
| [2025-01-07 20:51:15,285][00160] Num frames 2500... | |
| [2025-01-07 20:51:24,020][00160] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2025-01-07 20:51:24,022][00160] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2025-01-07 20:51:24,024][00160] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2025-01-07 20:51:24,026][00160] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2025-01-07 20:51:24,027][00160] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2025-01-07 20:51:24,030][00160] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2025-01-07 20:51:24,031][00160] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! | |
| [2025-01-07 20:51:24,033][00160] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2025-01-07 20:51:24,034][00160] Adding new argument 'push_to_hub'=True that is not in the saved config file! | |
| [2025-01-07 20:51:24,035][00160] Adding new argument 'hf_repository'='robotfarmer/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! | |
| [2025-01-07 20:51:24,036][00160] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2025-01-07 20:51:24,037][00160] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2025-01-07 20:51:24,039][00160] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2025-01-07 20:51:24,040][00160] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2025-01-07 20:51:24,043][00160] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2025-01-07 20:51:24,072][00160] RunningMeanStd input shape: (3, 72, 128) | |
| [2025-01-07 20:51:24,075][00160] RunningMeanStd input shape: (1,) | |
| [2025-01-07 20:51:24,088][00160] ConvEncoder: input_channels=3 | |
| [2025-01-07 20:51:24,125][00160] Conv encoder output size: 512 | |
| [2025-01-07 20:51:24,126][00160] Policy head output size: 512 | |
| [2025-01-07 20:51:24,151][00160] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2025-01-07 20:51:24,595][00160] Num frames 100... | |
| [2025-01-07 20:51:24,721][00160] Num frames 200... | |
| [2025-01-07 20:51:24,850][00160] Num frames 300... | |
| [2025-01-07 20:51:24,977][00160] Num frames 400... | |
| [2025-01-07 20:51:25,101][00160] Num frames 500... | |
| [2025-01-07 20:51:25,232][00160] Num frames 600... | |
| [2025-01-07 20:51:25,359][00160] Num frames 700... | |
| [2025-01-07 20:51:25,480][00160] Num frames 800... | |
| [2025-01-07 20:51:25,615][00160] Num frames 900... | |
| [2025-01-07 20:51:25,739][00160] Num frames 1000... | |
| [2025-01-07 20:51:25,868][00160] Num frames 1100... | |
| [2025-01-07 20:51:25,999][00160] Num frames 1200... | |
| [2025-01-07 20:51:26,129][00160] Num frames 1300... | |
| [2025-01-07 20:51:26,287][00160] Avg episode rewards: #0: 28.760, true rewards: #0: 13.760 | |
| [2025-01-07 20:51:26,289][00160] Avg episode reward: 28.760, avg true_objective: 13.760 | |
| [2025-01-07 20:51:26,321][00160] Num frames 1400... | |
| [2025-01-07 20:51:26,447][00160] Num frames 1500... | |
| [2025-01-07 20:51:26,575][00160] Num frames 1600... | |
| [2025-01-07 20:51:26,714][00160] Num frames 1700... | |
| [2025-01-07 20:51:26,843][00160] Num frames 1800... | |
| [2025-01-07 20:51:26,972][00160] Num frames 1900... | |
| [2025-01-07 20:51:27,054][00160] Avg episode rewards: #0: 18.100, true rewards: #0: 9.600 | |
| [2025-01-07 20:51:27,057][00160] Avg episode reward: 18.100, avg true_objective: 9.600 | |
| [2025-01-07 20:51:27,164][00160] Num frames 2000... | |
| [2025-01-07 20:51:27,301][00160] Num frames 2100... | |
| [2025-01-07 20:51:27,419][00160] Num frames 2200... | |
| [2025-01-07 20:51:27,546][00160] Num frames 2300... | |
| [2025-01-07 20:51:27,679][00160] Num frames 2400... | |
| [2025-01-07 20:51:27,815][00160] Avg episode rewards: #0: 15.537, true rewards: #0: 8.203 | |
| [2025-01-07 20:51:27,816][00160] Avg episode reward: 15.537, avg true_objective: 8.203 | |
| [2025-01-07 20:51:27,875][00160] Num frames 2500... | |
| [2025-01-07 20:51:27,999][00160] Num frames 2600... | |
| [2025-01-07 20:51:28,118][00160] Num frames 2700... | |
| [2025-01-07 20:51:28,250][00160] Num frames 2800... | |
| [2025-01-07 20:51:28,375][00160] Num frames 2900... | |
| [2025-01-07 20:51:28,499][00160] Num frames 3000... | |
| [2025-01-07 20:51:28,627][00160] Num frames 3100... | |
| [2025-01-07 20:51:28,765][00160] Num frames 3200... | |
| [2025-01-07 20:51:28,887][00160] Num frames 3300... | |
| [2025-01-07 20:51:29,017][00160] Num frames 3400... | |
| [2025-01-07 20:51:29,147][00160] Num frames 3500... | |
| [2025-01-07 20:51:29,278][00160] Num frames 3600... | |
| [2025-01-07 20:51:29,403][00160] Num frames 3700... | |
| [2025-01-07 20:51:29,539][00160] Num frames 3800... | |
| [2025-01-07 20:51:29,693][00160] Num frames 3900... | |
| [2025-01-07 20:51:29,842][00160] Avg episode rewards: #0: 20.923, true rewards: #0: 9.922 | |
| [2025-01-07 20:51:29,844][00160] Avg episode reward: 20.923, avg true_objective: 9.922 | |
| [2025-01-07 20:51:29,886][00160] Num frames 4000... | |
| [2025-01-07 20:51:30,013][00160] Num frames 4100... | |
| [2025-01-07 20:51:30,149][00160] Num frames 4200... | |
| [2025-01-07 20:51:30,281][00160] Num frames 4300... | |
| [2025-01-07 20:51:30,410][00160] Num frames 4400... | |
| [2025-01-07 20:51:30,536][00160] Num frames 4500... | |
| [2025-01-07 20:51:30,660][00160] Num frames 4600... | |
| [2025-01-07 20:51:30,796][00160] Num frames 4700... | |
| [2025-01-07 20:51:30,925][00160] Num frames 4800... | |
| [2025-01-07 20:51:31,054][00160] Num frames 4900... | |
| [2025-01-07 20:51:31,178][00160] Num frames 5000... | |
| [2025-01-07 20:51:31,317][00160] Num frames 5100... | |
| [2025-01-07 20:51:31,503][00160] Num frames 5200... | |
| [2025-01-07 20:51:31,592][00160] Avg episode rewards: #0: 22.034, true rewards: #0: 10.434 | |
| [2025-01-07 20:51:31,594][00160] Avg episode reward: 22.034, avg true_objective: 10.434 | |
| [2025-01-07 20:51:31,740][00160] Num frames 5300... | |
| [2025-01-07 20:51:31,918][00160] Num frames 5400... | |
| [2025-01-07 20:51:32,090][00160] Num frames 5500... | |
| [2025-01-07 20:51:32,281][00160] Num frames 5600... | |
| [2025-01-07 20:51:32,456][00160] Num frames 5700... | |
| [2025-01-07 20:51:32,644][00160] Num frames 5800... | |
| [2025-01-07 20:51:32,833][00160] Num frames 5900... | |
| [2025-01-07 20:51:33,019][00160] Num frames 6000... | |
| [2025-01-07 20:51:33,209][00160] Avg episode rewards: #0: 21.958, true rewards: #0: 10.125 | |
| [2025-01-07 20:51:33,211][00160] Avg episode reward: 21.958, avg true_objective: 10.125 | |
| [2025-01-07 20:51:33,265][00160] Num frames 6100... | |
| [2025-01-07 20:51:33,447][00160] Num frames 6200... | |
| [2025-01-07 20:51:33,628][00160] Num frames 6300... | |
| [2025-01-07 20:51:33,812][00160] Num frames 6400... | |
| [2025-01-07 20:51:33,993][00160] Num frames 6500... | |
| [2025-01-07 20:51:34,118][00160] Num frames 6600... | |
| [2025-01-07 20:51:34,248][00160] Num frames 6700... | |
| [2025-01-07 20:51:34,379][00160] Num frames 6800... | |
| [2025-01-07 20:51:34,507][00160] Num frames 6900... | |
| [2025-01-07 20:51:34,634][00160] Num frames 7000... | |
| [2025-01-07 20:51:34,766][00160] Num frames 7100... | |
| [2025-01-07 20:51:34,906][00160] Num frames 7200... | |
| [2025-01-07 20:51:35,043][00160] Num frames 7300... | |
| [2025-01-07 20:51:35,174][00160] Num frames 7400... | |
| [2025-01-07 20:51:35,310][00160] Num frames 7500... | |
| [2025-01-07 20:51:35,438][00160] Num frames 7600... | |
| [2025-01-07 20:51:35,592][00160] Avg episode rewards: #0: 23.679, true rewards: #0: 10.964 | |
| [2025-01-07 20:51:35,594][00160] Avg episode reward: 23.679, avg true_objective: 10.964 | |
| [2025-01-07 20:51:35,633][00160] Num frames 7700... | |
| [2025-01-07 20:51:35,762][00160] Num frames 7800... | |
| [2025-01-07 20:51:35,894][00160] Num frames 7900... | |
| [2025-01-07 20:51:36,026][00160] Num frames 8000... | |
| [2025-01-07 20:51:36,156][00160] Num frames 8100... | |
| [2025-01-07 20:51:36,294][00160] Num frames 8200... | |
| [2025-01-07 20:51:36,426][00160] Num frames 8300... | |
| [2025-01-07 20:51:36,564][00160] Num frames 8400... | |
| [2025-01-07 20:51:36,697][00160] Num frames 8500... | |
| [2025-01-07 20:51:36,830][00160] Num frames 8600... | |
| [2025-01-07 20:51:36,968][00160] Num frames 8700... | |
| [2025-01-07 20:51:37,098][00160] Num frames 8800... | |
| [2025-01-07 20:51:37,233][00160] Num frames 8900... | |
| [2025-01-07 20:51:37,357][00160] Num frames 9000... | |
| [2025-01-07 20:51:37,480][00160] Num frames 9100... | |
| [2025-01-07 20:51:37,607][00160] Num frames 9200... | |
| [2025-01-07 20:51:37,730][00160] Num frames 9300... | |
| [2025-01-07 20:51:37,860][00160] Num frames 9400... | |
| [2025-01-07 20:51:37,995][00160] Num frames 9500... | |
| [2025-01-07 20:51:38,128][00160] Avg episode rewards: #0: 26.579, true rewards: #0: 11.954 | |
| [2025-01-07 20:51:38,129][00160] Avg episode reward: 26.579, avg true_objective: 11.954 | |
| [2025-01-07 20:51:38,179][00160] Num frames 9600... | |
| [2025-01-07 20:51:38,316][00160] Num frames 9700... | |
| [2025-01-07 20:51:38,446][00160] Num frames 9800... | |
| [2025-01-07 20:51:38,573][00160] Num frames 9900... | |
| [2025-01-07 20:51:38,702][00160] Num frames 10000... | |
| [2025-01-07 20:51:38,826][00160] Num frames 10100... | |
| [2025-01-07 20:51:38,957][00160] Num frames 10200... | |
| [2025-01-07 20:51:39,093][00160] Num frames 10300... | |
| [2025-01-07 20:51:39,226][00160] Num frames 10400... | |
| [2025-01-07 20:51:39,353][00160] Num frames 10500... | |
| [2025-01-07 20:51:39,487][00160] Num frames 10600... | |
| [2025-01-07 20:51:39,647][00160] Avg episode rewards: #0: 26.314, true rewards: #0: 11.870 | |
| [2025-01-07 20:51:39,650][00160] Avg episode reward: 26.314, avg true_objective: 11.870 | |
| [2025-01-07 20:51:39,675][00160] Num frames 10700... | |
| [2025-01-07 20:51:39,802][00160] Num frames 10800... | |
| [2025-01-07 20:51:39,933][00160] Num frames 10900... | |
| [2025-01-07 20:51:40,073][00160] Num frames 11000... | |
| [2025-01-07 20:51:40,212][00160] Num frames 11100... | |
| [2025-01-07 20:51:40,345][00160] Num frames 11200... | |
| [2025-01-07 20:51:40,474][00160] Num frames 11300... | |
| [2025-01-07 20:51:40,601][00160] Num frames 11400... | |
| [2025-01-07 20:51:40,749][00160] Num frames 11500... | |
| [2025-01-07 20:51:40,907][00160] Avg episode rewards: #0: 25.279, true rewards: #0: 11.579 | |
| [2025-01-07 20:51:40,908][00160] Avg episode reward: 25.279, avg true_objective: 11.579 | |
| [2025-01-07 20:52:48,654][00160] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |