{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9268479943275452, "min": 0.9268479943275452, "max": 2.872371196746826, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8849.544921875, "min": 8849.544921875, "max": 29415.953125, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.850757598876953, "min": 0.49157002568244934, "max": 12.850757598876953, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2505.897705078125, "min": 95.36458587646484, "max": 2593.2705078125, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0722709397943582, "min": 0.0640588521939136, "max": 0.0761550700556779, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2890837591774328, "min": 0.25934755381896657, "max": 0.3616007176183213, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1863731088518512, "min": 0.1267329887509821, "max": 0.2944844097775572, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7454924354074048, "min": 0.5069319550039284, "max": 1.3869839334020426, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.681818181818183, "min": 3.727272727272727, "max": 25.681818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1130.0, "min": 164.0, "max": 1392.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.681818181818183, "min": 3.727272727272727, "max": 25.681818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1130.0, "min": 164.0, "max": 1392.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1673727108", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget-nature_cnn --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1673727533" }, "total": 424.89689197999996, "count": 1, "self": 0.4229490420000275, "children": { "run_training.setup": { "total": 0.1093391540000539, "count": 1, "self": 0.1093391540000539 }, "TrainerController.start_learning": { "total": 424.3646037839999, "count": 1, "self": 0.515026282022518, "children": { "TrainerController._reset_env": { "total": 6.164795256999923, "count": 1, "self": 6.164795256999923 }, "TrainerController.advance": { "total": 417.55850797497783, "count": 18201, "self": 0.25266607996672974, "children": { "env_step": { "total": 417.3058418950111, "count": 18201, "self": 272.70386744500183, "children": { "SubprocessEnvManager._take_step": { "total": 144.33831795802598, "count": 18201, "self": 1.3555206449827892, "children": { "TorchPolicy.evaluate": { "total": 142.9827973130432, "count": 18201, "self": 31.8605759190732, "children": { "TorchPolicy.sample_actions": { "total": 111.12222139397, "count": 18201, "self": 111.12222139397 } } } } }, "workers": { "total": 0.26365649198328356, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 423.1508067570253, "count": 18201, "is_parallel": true, "self": 203.34157348599274, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019309989997964294, "count": 1, "is_parallel": true, "self": 0.000678426999684234, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012525720001121954, "count": 10, "is_parallel": true, "self": 0.0012525720001121954 } } }, "UnityEnvironment.step": { "total": 0.04584217100000387, "count": 1, "is_parallel": true, "self": 0.0005011769999327953, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003017870001258416, "count": 1, "is_parallel": true, "self": 0.0003017870001258416 }, "communicator.exchange": { "total": 0.0430484080000042, "count": 1, "is_parallel": true, "self": 0.0430484080000042 }, "steps_from_proto": { "total": 0.0019907989999410347, "count": 1, "is_parallel": true, "self": 0.00048542200011070236, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015053769998303324, "count": 10, "is_parallel": true, "self": 0.0015053769998303324 } } } } } } }, "UnityEnvironment.step": { "total": 219.80923327103255, "count": 18200, "is_parallel": true, "self": 8.326347810035486, "children": { "UnityEnvironment._generate_step_input": { "total": 4.811132445990779, "count": 18200, "is_parallel": true, "self": 4.811132445990779 }, "communicator.exchange": { "total": 174.3423243809707, "count": 18200, "is_parallel": true, "self": 174.3423243809707 }, "steps_from_proto": { "total": 32.329428634035594, "count": 18200, "is_parallel": true, "self": 6.520087415919988, "children": { "_process_rank_one_or_two_observation": { "total": 25.809341218115605, "count": 182000, "is_parallel": true, "self": 25.809341218115605 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.3527999878278933e-05, "count": 1, "self": 4.3527999878278933e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 414.81130502598194, "count": 326572, "is_parallel": true, "self": 8.523008061926248, "children": { "process_trajectory": { "total": 236.09358654105517, "count": 326572, "is_parallel": true, "self": 235.37957152105537, "children": { "RLTrainer._checkpoint": { "total": 0.7140150199998061, "count": 4, "is_parallel": true, "self": 0.7140150199998061 } } }, "_update_policy": { "total": 170.19471042300052, "count": 90, "is_parallel": true, "self": 44.2483758919966, "children": { "TorchPPOOptimizer.update": { "total": 125.94633453100391, "count": 4587, "is_parallel": true, "self": 125.94633453100391 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12623074199973416, "count": 1, "self": 0.0008290529995065299, "children": { "RLTrainer._checkpoint": { "total": 0.12540168900022763, "count": 1, "self": 0.12540168900022763 } } } } } } }