Hugging Face's logo

sighmon
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files Metrics Community
sighmon commited on
Commit
a3f849a
·
verified ·
1 Parent(s): aad8766

First Push

Browse files
Files changed (22) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-149984.onnx +1 -1
  3. SnowballTarget/SnowballTarget-149984.pt +1 -1
  4. SnowballTarget/SnowballTarget-199984.onnx +1 -1
  5. SnowballTarget/SnowballTarget-199984.pt +1 -1
  6. SnowballTarget/SnowballTarget-249944.onnx +3 -0
  7. SnowballTarget/SnowballTarget-249944.pt +3 -0
  8. SnowballTarget/SnowballTarget-299968.onnx +3 -0
  9. SnowballTarget/SnowballTarget-299968.pt +3 -0
  10. SnowballTarget/SnowballTarget-300608.onnx +3 -0
  11. SnowballTarget/SnowballTarget-300608.pt +3 -0
  12. SnowballTarget/SnowballTarget-49936.onnx +1 -1
  13. SnowballTarget/SnowballTarget-49936.pt +1 -1
  14. SnowballTarget/SnowballTarget-99960.onnx +1 -1
  15. SnowballTarget/SnowballTarget-99960.pt +1 -1
  16. SnowballTarget/checkpoint.pt +1 -1
  17. SnowballTarget/events.out.tfevents.1738841115.a507baff72c6.8589.0 +3 -0
  18. config.json +1 -1
  19. configuration.yaml +3 -3
  20. run_logs/Player-0.log +15 -18
  21. run_logs/timers.json +161 -161
  22. run_logs/training_status.json +44 -26
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0232ff2741ab2dcc09c58cae49e63f63eda126501590ebcd44b18b38ba4632c6
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc917b2d0175837dc3783c86c3f43d325ef6cc62194f129bfb8be862d9c97628
3
  size 650646
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:10b36c060fc3710fa68f1839985a13bfbe79af9b5a3ce8e2e2ca3cb2a88edfb1
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:646d9d0ef2d58111eedcbf3ae48011b881c7bc2d0153f36034bfb2e87e61e429
3
  size 650646
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6146da1cbdafabcd0fc710f51985f26bfa112b82234bfd0aad82e5d7c14104f3
3
  size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5a5005b3f1a5f54dfe33885d5e4d9e53b897aeba1ae9f47d56d13f3c0b6b9fc
3
  size 3850075
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0232ff2741ab2dcc09c58cae49e63f63eda126501590ebcd44b18b38ba4632c6
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:849bb86a7f8992f05d5e2615d0eac1c93607e81f295cb68b38dc8ba9a08fcd8a
3
  size 650646
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbf286f1b84b047589b526025e21f1b0646b0d62bcc4f14c12e45428e5a6393e
3
  size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e66fa665c6f1abfa8e3b9089b076643910f5490ad0121e8ac6e444006329577
3
  size 3850075
SnowballTarget/SnowballTarget-249944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b5e62ae72777bcc2678d3fc85fe7172076418007486080d55f1fd7eef6b50fb
3
+ size 650646
SnowballTarget/SnowballTarget-249944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fccc76fee8534e22d9914e4fd7fd91c3297eb6b1afbce04e3a8b0ee5f2f4ab3c
3
+ size 3850075
SnowballTarget/SnowballTarget-299968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc917b2d0175837dc3783c86c3f43d325ef6cc62194f129bfb8be862d9c97628
3
+ size 650646
SnowballTarget/SnowballTarget-299968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c9bb833033494255e15e9d184f7af3a0e0367f19b7e77faa8550763410aa44e
3
+ size 3850075
SnowballTarget/SnowballTarget-300608.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc917b2d0175837dc3783c86c3f43d325ef6cc62194f129bfb8be862d9c97628
3
+ size 650646
SnowballTarget/SnowballTarget-300608.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20358795ec9571254eff728a2539e0102921e5587d22d50fc09b39161155211f
3
+ size 3850075
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f79ee4c7ec84f748db519f97da9701d73591f4f4eb08584dd31eff1fa5053f3
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46f5b42286e5f314ed4f9046b8fafce41af1f33543530451d36a61d3ffa1a0eb
3
  size 650646
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:791c85816f7337dfec06fed0c8560ba16724a79886297964cfd3632d20540a54
3
  size 3850000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0d77543309cfafd45f3cc5e02034273fa21da9e82e41277597808bd6019ec1c
3
  size 3850000
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e80bde27d644b0c1a83d23a45338d7c67284b051ab65da84dd7d24a88e5a153b
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0932b63401157ef8c63a28e8bb415be733e94a571e75caf0781dd367169bd642
3
  size 650646
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:10e89e18798e6ab7bce64cdfb22bbdbfefc340fc7184701034009dda1e85297d
3
  size 3850000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f6ba0b890211f79928710ca8bf9fc69c7005f3de3702ef334a18f8f12f5b800
3
  size 3850000
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a41448dd577ea940a25b1a63ec8b27ad2975bcfa9f851f0db8baf96a3ab413ea
3
  size 3849250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdf9446f1e562c6b0d8b1fcf80547caa23822d671b5635003ee2c02d6e939f6b
3
  size 3849250
SnowballTarget/events.out.tfevents.1738841115.a507baff72c6.8589.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba31f2294d1e6edf30b8589a7e5905c401418b8c1a9012dcb79d63b04e6972ba
3
+ size 31617
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0006, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 300000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget2", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -5,7 +5,7 @@ behaviors:
5
  hyperparameters:
6
  batch_size: 128
7
  buffer_size: 2048
8
- learning_rate: 0.0003
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
@@ -38,7 +38,7 @@ behaviors:
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
- max_steps: 200000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: false
@@ -66,7 +66,7 @@ engine_settings:
66
  no_graphics_monitor: false
67
  environment_parameters: null
68
  checkpoint_settings:
69
- run_id: SnowballTarget1
70
  initialize_from: null
71
  load_model: false
72
  resume: false
 
5
  hyperparameters:
6
  batch_size: 128
7
  buffer_size: 2048
8
+ learning_rate: 0.0006
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 300000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: false
 
66
  no_graphics_monitor: false
67
  environment_parameters: null
68
  checkpoint_settings:
69
+ run_id: SnowballTarget2
70
  initialize_from: null
71
  load_model: false
72
  resume: false
run_logs/Player-0.log CHANGED
@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarge
2
  Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
5
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
6
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
7
- Unable to load player prefs
8
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
9
  [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
10
  Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
34
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
35
  FMOD initialized on nosound output
36
  Begin MonoManager ReloadAssembly
37
- - Completed reload, in 0.087 seconds
38
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
39
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
40
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -45,7 +42,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
45
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
46
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
47
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
48
- UnloadTime: 0.670139 ms
49
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
50
  requesting resize 84 x 84
51
  Setting up 1 worker threads for Enlighten.
@@ -53,7 +50,7 @@ Memory Statistics:
53
  [ALLOC_TEMP_TLS] TLS Allocator
54
  StackAllocators :
55
  [ALLOC_TEMP_MAIN]
56
- Peak usage frame count: [8.0 KB-16.0 KB]: 5367 frames, [16.0 KB-32.0 KB]: 90 frames, [2.0 MB-4.0 MB]: 1 frames
57
  Initial Block Size 4.0 MB
58
  Current Block Size 4.0 MB
59
  Peak Allocated Bytes 2.0 MB
@@ -169,22 +166,22 @@ Memory Statistics:
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
- Peak main deferred allocation count 36
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
176
  Peak Allocated bytes 1.0 MB
177
  [ALLOC_DEFAULT_MAIN]
178
- Peak usage frame count: [4.0 MB-8.0 MB]: 5458 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 6.6 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
- Peak Allocated memory 17.9 MB
188
  Peak Large allocation bytes 16.0 MB
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 MB
@@ -213,13 +210,13 @@ Memory Statistics:
213
  Used Block count 1
214
  Peak Allocated bytes 1.0 MB
215
  [ALLOC_GFX_MAIN]
216
- Peak usage frame count: [32.0 KB-64.0 KB]: 5144 frames, [64.0 KB-128.0 KB]: 314 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 66.4 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
- Peak usage frame count: [32.0 KB-64.0 KB]: 5458 frames
223
  Requested Block Size 16.0 MB
224
  Peak Block count 1
225
  Peak Allocated memory 39.6 KB
@@ -231,13 +228,13 @@ Memory Statistics:
231
  Used Block count 1
232
  Peak Allocated bytes 1.0 MB
233
  [ALLOC_CACHEOBJECTS_MAIN]
234
- Peak usage frame count: [0.5 MB-1.0 MB]: 5458 frames
235
  Requested Block Size 4.0 MB
236
  Peak Block count 1
237
  Peak Allocated memory 0.6 MB
238
  Peak Large allocation bytes 0 B
239
  [ALLOC_CACHEOBJECTS_THREAD]
240
- Peak usage frame count: [0.5 MB-1.0 MB]: 5457 frames, [2.0 MB-4.0 MB]: 1 frames
241
  Requested Block Size 4.0 MB
242
  Peak Block count 1
243
  Peak Allocated memory 2.2 MB
@@ -249,13 +246,13 @@ Memory Statistics:
249
  Used Block count 1
250
  Peak Allocated bytes 1.0 MB
251
  [ALLOC_TYPETREE_MAIN]
252
- Peak usage frame count: [0-1.0 KB]: 5458 frames
253
  Requested Block Size 2.0 MB
254
  Peak Block count 1
255
  Peak Allocated memory 1.0 KB
256
  Peak Large allocation bytes 0 B
257
  [ALLOC_TYPETREE_THREAD]
258
- Peak usage frame count: [1.0 KB-2.0 KB]: 5458 frames
259
  Requested Block Size 2.0 MB
260
  Peak Block count 1
261
  Peak Allocated memory 1.7 KB
 
2
  Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
 
 
 
5
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
6
  [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
7
  Forcing GfxDevice: Null
 
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
+ - Completed reload, in 0.086 seconds
35
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
36
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
37
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 
42
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
43
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
44
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
45
+ UnloadTime: 0.657948 ms
46
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
47
  requesting resize 84 x 84
48
  Setting up 1 worker threads for Enlighten.
 
50
  [ALLOC_TEMP_TLS] TLS Allocator
51
  StackAllocators :
52
  [ALLOC_TEMP_MAIN]
53
+ Peak usage frame count: [8.0 KB-16.0 KB]: 8062 frames, [16.0 KB-32.0 KB]: 136 frames, [2.0 MB-4.0 MB]: 1 frames
54
  Initial Block Size 4.0 MB
55
  Current Block Size 4.0 MB
56
  Peak Allocated Bytes 2.0 MB
 
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
+ Peak main deferred allocation count 41
170
  [ALLOC_BUCKET]
171
  Large Block size 4.0 MB
172
  Used Block count 1
173
  Peak Allocated bytes 1.0 MB
174
  [ALLOC_DEFAULT_MAIN]
175
+ Peak usage frame count: [4.0 MB-8.0 MB]: 8199 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 7.5 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 8199 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
+ Peak Allocated memory 17.8 MB
185
  Peak Large allocation bytes 16.0 MB
186
  [ALLOC_TEMP_JOB_1_FRAME]
187
  Initial Block Size 2.0 MB
 
210
  Used Block count 1
211
  Peak Allocated bytes 1.0 MB
212
  [ALLOC_GFX_MAIN]
213
+ Peak usage frame count: [32.0 KB-64.0 KB]: 7544 frames, [64.0 KB-128.0 KB]: 655 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 66.8 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 8199 frames
220
  Requested Block Size 16.0 MB
221
  Peak Block count 1
222
  Peak Allocated memory 39.6 KB
 
228
  Used Block count 1
229
  Peak Allocated bytes 1.0 MB
230
  [ALLOC_CACHEOBJECTS_MAIN]
231
+ Peak usage frame count: [0.5 MB-1.0 MB]: 8199 frames
232
  Requested Block Size 4.0 MB
233
  Peak Block count 1
234
  Peak Allocated memory 0.6 MB
235
  Peak Large allocation bytes 0 B
236
  [ALLOC_CACHEOBJECTS_THREAD]
237
+ Peak usage frame count: [0.5 MB-1.0 MB]: 8198 frames, [2.0 MB-4.0 MB]: 1 frames
238
  Requested Block Size 4.0 MB
239
  Peak Block count 1
240
  Peak Allocated memory 2.2 MB
 
246
  Used Block count 1
247
  Peak Allocated bytes 1.0 MB
248
  [ALLOC_TYPETREE_MAIN]
249
+ Peak usage frame count: [0-1.0 KB]: 8199 frames
250
  Requested Block Size 2.0 MB
251
  Peak Block count 1
252
  Peak Allocated memory 1.0 KB
253
  Peak Large allocation bytes 0 B
254
  [ALLOC_TYPETREE_THREAD]
255
+ Peak usage frame count: [1.0 KB-2.0 KB]: 8199 frames
256
  Requested Block Size 2.0 MB
257
  Peak Block count 1
258
  Peak Allocated memory 1.7 KB
run_logs/timers.json CHANGED
@@ -2,213 +2,213 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.8479892611503601,
6
- "min": 0.8339678645133972,
7
- "max": 2.846102714538574,
8
- "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 8059.2900390625,
12
- "min": 8059.2900390625,
13
- "max": 29053.015625,
14
- "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 199984.0,
18
  "min": 9952.0,
19
- "max": 199984.0,
20
- "count": 20
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 199984.0,
24
  "min": 9952.0,
25
- "max": 199984.0,
26
- "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 12.924681663513184,
30
- "min": 0.25504982471466064,
31
- "max": 12.95297622680664,
32
- "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2520.31298828125,
36
- "min": 49.47966766357422,
37
- "max": 2642.4072265625,
38
- "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
- "value": 0.06724923797104138,
42
- "min": 0.06617977782865209,
43
- "max": 0.07539330540263714,
44
- "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
- "value": 0.2689969518841655,
48
- "min": 0.26471911131460835,
49
- "max": 0.3702839636419002,
50
- "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
- "value": 0.20466902355353037,
54
- "min": 0.12368225379888079,
55
- "max": 0.30925923213362694,
56
- "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
- "value": 0.8186760942141215,
60
- "min": 0.49472901519552315,
61
- "max": 1.4056900479629928,
62
- "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
- "value": 8.082097306000005e-06,
66
- "min": 8.082097306000005e-06,
67
- "max": 0.000291882002706,
68
- "count": 20
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
71
- "value": 3.232838922400002e-05,
72
- "min": 3.232838922400002e-05,
73
- "max": 0.00138516003828,
74
- "count": 20
75
  },
76
  "SnowballTarget.Policy.Epsilon.mean": {
77
- "value": 0.10269400000000001,
78
- "min": 0.10269400000000001,
79
- "max": 0.19729400000000002,
80
- "count": 20
81
  },
82
  "SnowballTarget.Policy.Epsilon.sum": {
83
- "value": 0.41077600000000003,
84
- "min": 0.41077600000000003,
85
- "max": 0.96172,
86
- "count": 20
87
  },
88
  "SnowballTarget.Policy.Beta.mean": {
89
- "value": 0.0001444306000000001,
90
- "min": 0.0001444306000000001,
91
- "max": 0.0048649706,
92
- "count": 20
93
  },
94
  "SnowballTarget.Policy.Beta.sum": {
95
- "value": 0.0005777224000000004,
96
- "min": 0.0005777224000000004,
97
- "max": 0.023089828,
98
- "count": 20
99
  },
100
  "SnowballTarget.Environment.EpisodeLength.mean": {
101
  "value": 199.0,
102
  "min": 199.0,
103
  "max": 199.0,
104
- "count": 20
105
  },
106
  "SnowballTarget.Environment.EpisodeLength.sum": {
107
- "value": 8756.0,
108
  "min": 8756.0,
109
  "max": 10945.0,
110
- "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.09090909090909,
114
- "min": 3.590909090909091,
115
- "max": 25.545454545454547,
116
- "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1104.0,
120
- "min": 158.0,
121
- "max": 1390.0,
122
- "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.09090909090909,
126
- "min": 3.590909090909091,
127
- "max": 25.545454545454547,
128
- "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1104.0,
132
- "min": 158.0,
133
- "max": 1390.0,
134
- "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
- "count": 20
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
- "count": 20
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1738839783",
152
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
153
- "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
  "mlagents_version": "1.2.0.dev0",
155
  "mlagents_envs_version": "1.2.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.6.0+cu124",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1738840217"
160
  },
161
- "total": 434.70822963800015,
162
  "count": 1,
163
- "self": 0.4364793520001058,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.028729053999995813,
167
  "count": 1,
168
- "self": 0.028729053999995813
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 434.24302123200005,
172
  "count": 1,
173
- "self": 0.36114231100032157,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 2.94747595299998,
177
  "count": 1,
178
- "self": 2.94747595299998
179
  },
180
  "TrainerController.advance": {
181
- "total": 430.82265969599973,
182
- "count": 18192,
183
- "self": 0.37832344999935685,
184
  "children": {
185
  "env_step": {
186
- "total": 305.15590313300527,
187
- "count": 18192,
188
- "self": 232.079336839004,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 72.85953587700567,
192
- "count": 18192,
193
- "self": 1.3123604120105483,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 71.54717546499512,
197
- "count": 18192,
198
- "self": 71.54717546499512
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.21703041699561254,
204
- "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 432.6002272829919,
209
- "count": 18192,
210
  "is_parallel": true,
211
- "self": 229.30488171300715,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
@@ -217,48 +217,48 @@
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
- "total": 0.00540246399998523,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0037950139999338717,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.001607450000051358,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.001607450000051358
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.035214628000062476,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0005524770000420176,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00044530599996051023,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00044530599996051023
244
  },
245
  "communicator.exchange": {
246
- "total": 0.0323690060000672,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.0323690060000672
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0018478389999927458,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00035134900019784254,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0014964899997949033,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0014964899997949033
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 203.29534556998476,
271
- "count": 18191,
272
  "is_parallel": true,
273
- "self": 9.739009922970467,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.441041090000681,
277
- "count": 18191,
278
  "is_parallel": true,
279
- "self": 5.441041090000681
280
  },
281
  "communicator.exchange": {
282
- "total": 156.51128903200697,
283
- "count": 18191,
284
  "is_parallel": true,
285
- "self": 156.51128903200697
286
  },
287
  "steps_from_proto": {
288
- "total": 31.60400552500664,
289
- "count": 18191,
290
  "is_parallel": true,
291
- "self": 5.715521263090295,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 25.888484261916346,
295
- "count": 181910,
296
  "is_parallel": true,
297
- "self": 25.888484261916346
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 125.28843311299511,
311
- "count": 18192,
312
- "self": 0.4405691199991679,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 27.681747976996007,
316
- "count": 18192,
317
- "self": 27.04832146699607,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 0.6334265099999357,
321
- "count": 4,
322
- "self": 0.6334265099999357
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 97.16611601599993,
328
- "count": 90,
329
- "self": 39.12451526600012,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 58.041600749999816,
333
- "count": 4587,
334
- "self": 58.041600749999816
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 8.960000741353724e-07,
344
  "count": 1,
345
- "self": 8.960000741353724e-07
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.1117423759999383,
349
  "count": 1,
350
- "self": 0.001228773000093497,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.1105136029998448,
354
  "count": 1,
355
- "self": 0.1105136029998448
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.7234710454940796,
6
+ "min": 0.7211694121360779,
7
+ "max": 2.8498573303222656,
8
+ "count": 30
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 7448.85791015625,
12
+ "min": 7241.0732421875,
13
+ "max": 29091.34375,
14
+ "count": 30
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 299968.0,
18
  "min": 9952.0,
19
+ "max": 299968.0,
20
+ "count": 30
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 299968.0,
24
  "min": 9952.0,
25
+ "max": 299968.0,
26
+ "count": 30
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.744291305541992,
30
+ "min": 0.17775389552116394,
31
+ "max": 13.925162315368652,
32
+ "count": 30
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2803.83544921875,
36
+ "min": 34.484256744384766,
37
+ "max": 2854.658203125,
38
+ "count": 30
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
+ "value": 0.07054175772303578,
42
+ "min": 0.06297348507645188,
43
+ "max": 0.07708247474967685,
44
+ "count": 30
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
+ "value": 0.3527087886151789,
48
+ "min": 0.25189394030580753,
49
+ "max": 0.3654153714853558,
50
+ "count": 30
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
+ "value": 0.18940478095821306,
54
+ "min": 0.10031758798583064,
55
+ "max": 0.2665141351959285,
56
+ "count": 30
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
+ "value": 0.9470239047910652,
60
+ "min": 0.40127035194332256,
61
+ "max": 1.2888355453809104,
62
+ "count": 30
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
+ "value": 1.0576098237333326e-05,
66
+ "min": 1.0576098237333326e-05,
67
+ "max": 0.0005891760018039999,
68
+ "count": 30
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
71
+ "value": 5.288049118666663e-05,
72
+ "min": 5.288049118666663e-05,
73
+ "max": 0.0028468800255199997,
74
+ "count": 30
75
  },
76
  "SnowballTarget.Policy.Epsilon.mean": {
77
+ "value": 0.10176266666666667,
78
+ "min": 0.10176266666666667,
79
+ "max": 0.198196,
80
+ "count": 30
81
  },
82
  "SnowballTarget.Policy.Epsilon.sum": {
83
+ "value": 0.5088133333333333,
84
+ "min": 0.42025066666666666,
85
+ "max": 0.97448,
86
+ "count": 30
87
  },
88
  "SnowballTarget.Policy.Beta.mean": {
89
+ "value": 9.795706666666662e-05,
90
+ "min": 9.795706666666662e-05,
91
+ "max": 0.0049099804000000006,
92
+ "count": 30
93
  },
94
  "SnowballTarget.Policy.Beta.sum": {
95
+ "value": 0.0004897853333333331,
96
+ "min": 0.0004897853333333331,
97
+ "max": 0.023726551999999998,
98
+ "count": 30
99
  },
100
  "SnowballTarget.Environment.EpisodeLength.mean": {
101
  "value": 199.0,
102
  "min": 199.0,
103
  "max": 199.0,
104
+ "count": 30
105
  },
106
  "SnowballTarget.Environment.EpisodeLength.sum": {
107
+ "value": 10945.0,
108
  "min": 8756.0,
109
  "max": 10945.0,
110
+ "count": 30
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 26.672727272727272,
114
+ "min": 2.8636363636363638,
115
+ "max": 27.236363636363638,
116
+ "count": 30
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1467.0,
120
+ "min": 126.0,
121
+ "max": 1498.0,
122
+ "count": 30
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 26.672727272727272,
126
+ "min": 2.8636363636363638,
127
+ "max": 27.236363636363638,
128
+ "count": 30
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1467.0,
132
+ "min": 126.0,
133
+ "max": 1498.0,
134
+ "count": 30
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 30
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 30
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1738841115",
152
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
153
+ "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics",
154
  "mlagents_version": "1.2.0.dev0",
155
  "mlagents_envs_version": "1.2.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.6.0+cu124",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1738841781"
160
  },
161
+ "total": 666.8529377719999,
162
  "count": 1,
163
+ "self": 0.755558695000218,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.021626193999964016,
167
  "count": 1,
168
+ "self": 0.021626193999964016
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 666.0757528829997,
172
  "count": 1,
173
+ "self": 0.6140667149784349,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 1.9851342710001063,
177
  "count": 1,
178
+ "self": 1.9851342710001063
179
  },
180
  "TrainerController.advance": {
181
+ "total": 663.3440004820209,
182
+ "count": 27328,
183
+ "self": 0.6185695410408698,
184
  "children": {
185
  "env_step": {
186
+ "total": 472.5973576210047,
187
+ "count": 27328,
188
+ "self": 358.4394442549976,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 113.79617522099147,
192
+ "count": 27328,
193
+ "self": 2.0803244800029006,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 111.71585074098857,
197
+ "count": 27328,
198
+ "self": 111.71585074098857
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.361738145015579,
204
+ "count": 27328,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 663.8068631400324,
209
+ "count": 27328,
210
  "is_parallel": true,
211
+ "self": 350.9226043930855,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0021581409998816525,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0006682499993075908,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0014898910005740618,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0014898910005740618
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.03621925500010548,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0005921619999753602,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0004401940000207105,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0004401940000207105
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.03332988300007855,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.03332988300007855
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0018570160000308533,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0003611639995142468,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0014958520005166065,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0014958520005166065
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 312.8842587469469,
271
+ "count": 27327,
272
  "is_parallel": true,
273
+ "self": 14.593478721860492,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 8.235549691996539,
277
+ "count": 27327,
278
  "is_parallel": true,
279
+ "self": 8.235549691996539
280
  },
281
  "communicator.exchange": {
282
+ "total": 241.94320678205963,
283
+ "count": 27327,
284
  "is_parallel": true,
285
+ "self": 241.94320678205963
286
  },
287
  "steps_from_proto": {
288
+ "total": 48.112023551030234,
289
+ "count": 27327,
290
  "is_parallel": true,
291
+ "self": 8.818129458982867,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 39.29389409204737,
295
+ "count": 273270,
296
  "is_parallel": true,
297
+ "self": 39.29389409204737
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 190.12807331997533,
311
+ "count": 27328,
312
+ "self": 0.7779899960366947,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 41.7558608249451,
316
+ "count": 27328,
317
+ "self": 40.93711971194466,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 0.8187411130004421,
321
+ "count": 6,
322
+ "self": 0.8187411130004421
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 147.59422249899353,
328
+ "count": 136,
329
+ "self": 58.50659884900074,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 89.08762364999279,
333
+ "count": 6933,
334
+ "self": 89.08762364999279
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 1.3280000530357938e-06,
344
  "count": 1,
345
+ "self": 1.3280000530357938e-06
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.13255008700025428,
349
  "count": 1,
350
+ "self": 0.0012406210003064189,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.13130946599994786,
354
  "count": 1,
355
+ "self": 0.13130946599994786
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -3,57 +3,75 @@
3
  "checkpoints": [
4
  {
5
  "steps": 49936,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 15.0,
8
- "creation_time": 1738839892.0946763,
9
  "auxillary_file_paths": [
10
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
12
  },
13
  {
14
  "steps": 99960,
15
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
- "reward": 22.727272727272727,
17
- "creation_time": 1738840002.7379124,
18
  "auxillary_file_paths": [
19
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
21
  },
22
  {
23
  "steps": 149984,
24
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
- "reward": 25.09090909090909,
26
- "creation_time": 1738840112.4691732,
27
  "auxillary_file_paths": [
28
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
30
  },
31
  {
32
  "steps": 199984,
33
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 25.181818181818183,
35
- "creation_time": 1738840217.2885532,
36
  "auxillary_file_paths": [
37
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
- "steps": 200112,
42
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
- "reward": 25.181818181818183,
44
- "creation_time": 1738840217.4073849,
45
  "auxillary_file_paths": [
46
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
- "steps": 200112,
52
- "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
- "reward": 25.181818181818183,
54
- "creation_time": 1738840217.4073849,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
3
  "checkpoints": [
4
  {
5
  "steps": 49936,
6
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 17.545454545454547,
8
+ "creation_time": 1738841224.822375,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
12
  },
13
  {
14
  "steps": 99960,
15
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.onnx",
16
+ "reward": 23.272727272727273,
17
+ "creation_time": 1738841334.5716143,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
21
  },
22
  {
23
  "steps": 149984,
24
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.onnx",
25
+ "reward": 25.0,
26
+ "creation_time": 1738841444.7629015,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
30
  },
31
  {
32
  "steps": 199984,
33
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.onnx",
34
+ "reward": 26.0,
35
+ "creation_time": 1738841554.4360917,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 249944,
42
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-249944.onnx",
43
+ "reward": 26.545454545454547,
44
+ "creation_time": 1738841665.3302934,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-249944.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 299968,
51
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-299968.onnx",
52
+ "reward": 26.272727272727273,
53
+ "creation_time": 1738841780.9258573,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-299968.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 300608,
60
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-300608.onnx",
61
+ "reward": 26.272727272727273,
62
+ "creation_time": 1738841781.1539752,
63
+ "auxillary_file_paths": [
64
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-300608.pt"
65
  ]
66
  }
67
  ],
68
  "final_checkpoint": {
69
+ "steps": 300608,
70
+ "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
71
+ "reward": 26.272727272727273,
72
+ "creation_time": 1738841781.1539752,
73
  "auxillary_file_paths": [
74
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-300608.pt"
75
  ]
76
  }
77
  },