|
{ |
|
"name": "root", |
|
"gauges": { |
|
"SnowballTarget.Policy.Entropy.mean": { |
|
"value": 0.9382531046867371, |
|
"min": 0.9382531046867371, |
|
"max": 2.863863706588745, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.Entropy.sum": { |
|
"value": 8958.4404296875, |
|
"min": 8958.4404296875, |
|
"max": 29328.828125, |
|
"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": 12.916909217834473, |
|
"min": 0.3568263053894043, |
|
"max": 12.916909217834473, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 2518.79736328125, |
|
"min": 69.22430419921875, |
|
"max": 2611.98095703125, |
|
"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": 0.06629789480208345, |
|
"min": 0.06309473126505812, |
|
"max": 0.07516176878524872, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.PolicyLoss.sum": { |
|
"value": 0.2651915792083338, |
|
"min": 0.25237892506023246, |
|
"max": 0.3758088439262436, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.ValueLoss.mean": { |
|
"value": 0.20105268287600256, |
|
"min": 0.10790547902933231, |
|
"max": 0.29046356597659634, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.ValueLoss.sum": { |
|
"value": 0.8042107315040102, |
|
"min": 0.43162191611732925, |
|
"max": 1.4523178298829817, |
|
"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": 25.636363636363637, |
|
"min": 3.1136363636363638, |
|
"max": 25.636363636363637, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Environment.CumulativeReward.sum": { |
|
"value": 1128.0, |
|
"min": 137.0, |
|
"max": 1410.0, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicReward.mean": { |
|
"value": 25.636363636363637, |
|
"min": 3.1136363636363638, |
|
"max": 25.636363636363637, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicReward.sum": { |
|
"value": 1128.0, |
|
"min": 137.0, |
|
"max": 1410.0, |
|
"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": "1718189995", |
|
"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": "2.3.0+cu121", |
|
"numpy_version": "1.23.5", |
|
"end_time_seconds": "1718190519" |
|
}, |
|
"total": 523.9329214200001, |
|
"count": 1, |
|
"self": 0.4435534799999914, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.06868051300000388, |
|
"count": 1, |
|
"self": 0.06868051300000388 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 523.4206874270001, |
|
"count": 1, |
|
"self": 0.7227511829856894, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 3.04605070599996, |
|
"count": 1, |
|
"self": 3.04605070599996 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 519.5546489470142, |
|
"count": 18202, |
|
"self": 0.33350899601464334, |
|
"children": { |
|
"env_step": { |
|
"total": 519.2211399509996, |
|
"count": 18202, |
|
"self": 341.57100485398473, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 177.29452228100615, |
|
"count": 18202, |
|
"self": 1.765624556018338, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 175.52889772498781, |
|
"count": 18202, |
|
"self": 175.52889772498781 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.3556128160087155, |
|
"count": 18202, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 521.800574462, |
|
"count": 18202, |
|
"is_parallel": true, |
|
"self": 259.6614858809995, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.005374671000026865, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0036736990001600134, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0017009719998668515, |
|
"count": 10, |
|
"is_parallel": true, |
|
"self": 0.0017009719998668515 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04756425000005038, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0007153479999715273, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004355209999857834, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004355209999857834 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04408644400007233, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04408644400007233 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0023269370000207346, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004339819998904204, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0018929550001303141, |
|
"count": 10, |
|
"is_parallel": true, |
|
"self": 0.0018929550001303141 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 262.13908858100046, |
|
"count": 18201, |
|
"is_parallel": true, |
|
"self": 11.77380685604112, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 6.167405628977804, |
|
"count": 18201, |
|
"is_parallel": true, |
|
"self": 6.167405628977804 |
|
}, |
|
"communicator.exchange": { |
|
"total": 204.80504381898402, |
|
"count": 18201, |
|
"is_parallel": true, |
|
"self": 204.80504381898402 |
|
}, |
|
"steps_from_proto": { |
|
"total": 39.392832276997524, |
|
"count": 18201, |
|
"is_parallel": true, |
|
"self": 7.6308491069934234, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 31.7619831700041, |
|
"count": 182010, |
|
"is_parallel": true, |
|
"self": 31.7619831700041 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 0.0001406180001595203, |
|
"count": 1, |
|
"self": 0.0001406180001595203, |
|
"children": { |
|
"thread_root": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"trainer_advance": { |
|
"total": 513.2075362960771, |
|
"count": 734010, |
|
"is_parallel": true, |
|
"self": 16.401592581071895, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 285.428082164006, |
|
"count": 734010, |
|
"is_parallel": true, |
|
"self": 284.02216603500597, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 1.4059161290000475, |
|
"count": 4, |
|
"is_parallel": true, |
|
"self": 1.4059161290000475 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 211.37786155099923, |
|
"count": 90, |
|
"is_parallel": true, |
|
"self": 67.0865895590008, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 144.29127199199843, |
|
"count": 4584, |
|
"is_parallel": true, |
|
"self": 144.29127199199843 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09709597300002315, |
|
"count": 1, |
|
"self": 0.0010068970000247646, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09608907599999839, |
|
"count": 1, |
|
"self": 0.09608907599999839 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |