|
{ |
|
"name": "root", |
|
"gauges": { |
|
"SnowballTarget.Policy.Entropy.mean": { |
|
"value": 1.0319377183914185, |
|
"min": 1.0319377183914185, |
|
"max": 2.8688135147094727, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.Entropy.sum": { |
|
"value": 9886.9951171875, |
|
"min": 9886.9951171875, |
|
"max": 29442.6328125, |
|
"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": 12.932798385620117, |
|
"min": 0.47161179780960083, |
|
"max": 12.932798385620117, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 2521.895751953125, |
|
"min": 91.49269104003906, |
|
"max": 2611.60400390625, |
|
"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": 0.0681352811034052, |
|
"min": 0.06050405375995694, |
|
"max": 0.07662602935406362, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.PolicyLoss.sum": { |
|
"value": 0.2725411244136208, |
|
"min": 0.24201621503982776, |
|
"max": 0.36819336616363396, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.ValueLoss.mean": { |
|
"value": 0.18516572298226402, |
|
"min": 0.13728359539413312, |
|
"max": 0.27557923980787685, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.ValueLoss.sum": { |
|
"value": 0.7406628919290561, |
|
"min": 0.5491343815765325, |
|
"max": 1.3719316542732949, |
|
"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": 25.59090909090909, |
|
"min": 3.8181818181818183, |
|
"max": 25.8, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Environment.CumulativeReward.sum": { |
|
"value": 1126.0, |
|
"min": 168.0, |
|
"max": 1419.0, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicReward.mean": { |
|
"value": 25.59090909090909, |
|
"min": 3.8181818181818183, |
|
"max": 25.8, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicReward.sum": { |
|
"value": 1126.0, |
|
"min": 168.0, |
|
"max": 1419.0, |
|
"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": "1705503848", |
|
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", |
|
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", |
|
"mlagents_version": "1.1.0.dev0", |
|
"mlagents_envs_version": "1.1.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "2.1.2+cu121", |
|
"numpy_version": "1.23.5", |
|
"end_time_seconds": "1705504481" |
|
}, |
|
"total": 632.6302948609998, |
|
"count": 1, |
|
"self": 0.549528357999634, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.11095558600004551, |
|
"count": 1, |
|
"self": 0.11095558600004551 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 631.9698109170001, |
|
"count": 1, |
|
"self": 0.9434447240109876, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 4.673069795000174, |
|
"count": 1, |
|
"self": 4.673069795000174 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 626.2413446899889, |
|
"count": 18203, |
|
"self": 0.5044643839494256, |
|
"children": { |
|
"env_step": { |
|
"total": 625.7368803060394, |
|
"count": 18203, |
|
"self": 487.5258038420254, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 137.5974386460075, |
|
"count": 18203, |
|
"self": 2.8293278890423608, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 134.76811075696514, |
|
"count": 18203, |
|
"self": 134.76811075696514 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.6136378180065094, |
|
"count": 18203, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 629.6761397239713, |
|
"count": 18203, |
|
"is_parallel": true, |
|
"self": 291.0192823709581, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.006948330000113856, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0047349050000775605, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0022134250000362954, |
|
"count": 10, |
|
"is_parallel": true, |
|
"self": 0.0022134250000362954 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.052495681999971566, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0008501510001224233, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004811019998669508, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004811019998669508 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.048785703000021385, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.048785703000021385 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.002378725999960807, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004705040000771987, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001908221999883608, |
|
"count": 10, |
|
"is_parallel": true, |
|
"self": 0.001908221999883608 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 338.65685735301327, |
|
"count": 18202, |
|
"is_parallel": true, |
|
"self": 16.545549778989425, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 8.380550775998017, |
|
"count": 18202, |
|
"is_parallel": true, |
|
"self": 8.380550775998017 |
|
}, |
|
"communicator.exchange": { |
|
"total": 266.7886107010215, |
|
"count": 18202, |
|
"is_parallel": true, |
|
"self": 266.7886107010215 |
|
}, |
|
"steps_from_proto": { |
|
"total": 46.9421460970043, |
|
"count": 18202, |
|
"is_parallel": true, |
|
"self": 9.688761600928729, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 37.25338449607557, |
|
"count": 182020, |
|
"is_parallel": true, |
|
"self": 37.25338449607557 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 9.904199987431639e-05, |
|
"count": 1, |
|
"self": 9.904199987431639e-05, |
|
"children": { |
|
"thread_root": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"trainer_advance": { |
|
"total": 619.1146909012004, |
|
"count": 816157, |
|
"is_parallel": true, |
|
"self": 18.71054635643668, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 328.98880406676176, |
|
"count": 816157, |
|
"is_parallel": true, |
|
"self": 328.37590394876156, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.6129001180001978, |
|
"count": 4, |
|
"is_parallel": true, |
|
"self": 0.6129001180001978 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 271.415340478002, |
|
"count": 90, |
|
"is_parallel": true, |
|
"self": 82.47133460901887, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 188.94400586898314, |
|
"count": 4587, |
|
"is_parallel": true, |
|
"self": 188.94400586898314 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.11185266600023169, |
|
"count": 1, |
|
"self": 0.0013782510004602955, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.1104744149997714, |
|
"count": 1, |
|
"self": 0.1104744149997714 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |