SatCat's picture
Snowball Push
31a2d07
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7115281224250793,
"min": 0.6629299521446228,
"max": 0.9079630374908447,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7161.5302734375,
"min": 6536.94677734375,
"max": 9288.4619140625,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 399992.0,
"min": 209960.0,
"max": 399992.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 399992.0,
"min": 209960.0,
"max": 399992.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.444840431213379,
"min": 12.738500595092773,
"max": 13.469720840454102,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2621.743896484375,
"min": 2437.1181640625,
"max": 2761.292724609375,
"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": 0.054253759806752816,
"min": 0.04208741953691721,
"max": 0.05702073462554395,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.21701503922701126,
"min": 0.19293302489897926,
"max": 0.2851036731277198,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2054526267403906,
"min": 0.1794286538479906,
"max": 0.22610665333993504,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8218105069615624,
"min": 0.7177146153919624,
"max": 1.1305332666996752,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.2970098702999983e-05,
"min": 1.2970098702999983e-05,
"max": 0.000485970051403,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 5.188039481199993e-05,
"min": 5.188039481199993e-05,
"max": 0.00230610026939,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.101297,
"min": 0.101297,
"max": 0.14859700000000003,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.405188,
"min": 0.405188,
"max": 0.7306100000000001,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 7.472029999999992e-05,
"min": 7.472029999999992e-05,
"max": 0.0024349903000000007,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00029888119999999966,
"min": 0.00029888119999999966,
"max": 0.011557439,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.545454545454547,
"min": 25.266666666666666,
"max": 26.545454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1168.0,
"min": 1115.0,
"max": 1459.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.545454545454547,
"min": 25.266666666666666,
"max": 26.545454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1168.0,
"min": 1115.0,
"max": 1459.0,
"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": "1673414239",
"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 --resume --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1673414680"
},
"total": 440.71028486299997,
"count": 1,
"self": 0.38347506300010537,
"children": {
"run_training.setup": {
"total": 0.10572927999987769,
"count": 1,
"self": 0.10572927999987769
},
"TrainerController.start_learning": {
"total": 440.22108052,
"count": 1,
"self": 0.5366430500075694,
"children": {
"TrainerController._reset_env": {
"total": 6.059100230000013,
"count": 1,
"self": 6.059100230000013
},
"TrainerController.advance": {
"total": 433.50041687299245,
"count": 18200,
"self": 0.2885586589804916,
"children": {
"env_step": {
"total": 433.21185821401195,
"count": 18200,
"self": 274.5489977980417,
"children": {
"SubprocessEnvManager._take_step": {
"total": 158.36610268898744,
"count": 18200,
"self": 1.4729232519805464,
"children": {
"TorchPolicy.evaluate": {
"total": 156.8931794370069,
"count": 18200,
"self": 36.39278627999488,
"children": {
"TorchPolicy.sample_actions": {
"total": 120.50039315701201,
"count": 18200,
"self": 120.50039315701201
}
}
}
}
},
"workers": {
"total": 0.29675772698283254,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 438.8011220610001,
"count": 18200,
"is_parallel": true,
"self": 206.61290676500016,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020631649999813817,
"count": 1,
"is_parallel": true,
"self": 0.0006697050000639138,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001393459999917468,
"count": 10,
"is_parallel": true,
"self": 0.001393459999917468
}
}
},
"UnityEnvironment.step": {
"total": 0.03586083100003634,
"count": 1,
"is_parallel": true,
"self": 0.00044598399995265936,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00031886100009614893,
"count": 1,
"is_parallel": true,
"self": 0.00031886100009614893
},
"communicator.exchange": {
"total": 0.03305295800009844,
"count": 1,
"is_parallel": true,
"self": 0.03305295800009844
},
"steps_from_proto": {
"total": 0.002043027999889091,
"count": 1,
"is_parallel": true,
"self": 0.0004791010001099494,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015639269997791416,
"count": 10,
"is_parallel": true,
"self": 0.0015639269997791416
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 232.18821529599995,
"count": 18199,
"is_parallel": true,
"self": 8.75898565398802,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.414445926994176,
"count": 18199,
"is_parallel": true,
"self": 5.414445926994176
},
"communicator.exchange": {
"total": 184.78614386901427,
"count": 18199,
"is_parallel": true,
"self": 184.78614386901427
},
"steps_from_proto": {
"total": 33.22863984600349,
"count": 18199,
"is_parallel": true,
"self": 7.149076616001366,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.079563230002123,
"count": 181990,
"is_parallel": true,
"self": 26.079563230002123
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 6.071899997550645e-05,
"count": 1,
"self": 6.071899997550645e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 430.1034648070547,
"count": 366286,
"is_parallel": true,
"self": 10.175957946105882,
"children": {
"process_trajectory": {
"total": 260.1607287349482,
"count": 366286,
"is_parallel": true,
"self": 259.40676113694826,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7539675979999174,
"count": 4,
"is_parallel": true,
"self": 0.7539675979999174
}
}
},
"_update_policy": {
"total": 159.76677812600064,
"count": 90,
"is_parallel": true,
"self": 45.96032436099654,
"children": {
"TorchPPOOptimizer.update": {
"total": 113.80645376500411,
"count": 2967,
"is_parallel": true,
"self": 113.80645376500411
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12485964799998328,
"count": 1,
"self": 0.0010934790000192152,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12376616899996407,
"count": 1,
"self": 0.12376616899996407
}
}
}
}
}
}
}