OldCrazyCoder's picture
First Push
4c8690e
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8926136493682861,
"min": 0.8926136493682861,
"max": 2.871182918548584,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8542.3125,
"min": 8542.3125,
"max": 29466.94921875,
"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": 12.98139762878418,
"min": 0.3165425956249237,
"max": 12.98139762878418,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2531.37255859375,
"min": 61.409263610839844,
"max": 2644.6455078125,
"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": 0.06595829092924867,
"min": 0.06308626674353053,
"max": 0.07878927300200803,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26383316371699467,
"min": 0.25736235837650706,
"max": 0.3555851165164153,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19348672879677192,
"min": 0.11200323062446699,
"max": 0.28445402857135327,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7739469151870877,
"min": 0.44801292249786795,
"max": 1.4222701428567663,
"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": 25.545454545454547,
"min": 3.409090909090909,
"max": 25.75,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1124.0,
"min": 150.0,
"max": 1405.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.545454545454547,
"min": 3.409090909090909,
"max": 25.75,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1124.0,
"min": 150.0,
"max": 1405.0,
"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": "1692815962",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1692816533"
},
"total": 570.7482722660001,
"count": 1,
"self": 0.488080507000177,
"children": {
"run_training.setup": {
"total": 0.04818699700001616,
"count": 1,
"self": 0.04818699700001616
},
"TrainerController.start_learning": {
"total": 570.2120047619999,
"count": 1,
"self": 0.7485763469868516,
"children": {
"TrainerController._reset_env": {
"total": 4.5028742719999855,
"count": 1,
"self": 4.5028742719999855
},
"TrainerController.advance": {
"total": 564.8024324760131,
"count": 18203,
"self": 0.3841869310159609,
"children": {
"env_step": {
"total": 564.4182455449971,
"count": 18203,
"self": 413.75514200598604,
"children": {
"SubprocessEnvManager._take_step": {
"total": 150.294701669005,
"count": 18203,
"self": 2.268005064009003,
"children": {
"TorchPolicy.evaluate": {
"total": 148.026696604996,
"count": 18203,
"self": 148.026696604996
}
}
},
"workers": {
"total": 0.36840187000609603,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 567.9849545249946,
"count": 18203,
"is_parallel": true,
"self": 260.09247068899333,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0062781699999732155,
"count": 1,
"is_parallel": true,
"self": 0.0047129360000326415,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001565233999940574,
"count": 10,
"is_parallel": true,
"self": 0.001565233999940574
}
}
},
"UnityEnvironment.step": {
"total": 0.0550483519999716,
"count": 1,
"is_parallel": true,
"self": 0.0007274109998434142,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004871240000738908,
"count": 1,
"is_parallel": true,
"self": 0.0004871240000738908
},
"communicator.exchange": {
"total": 0.051385430999971504,
"count": 1,
"is_parallel": true,
"self": 0.051385430999971504
},
"steps_from_proto": {
"total": 0.0024483860000827917,
"count": 1,
"is_parallel": true,
"self": 0.0005790400002751994,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018693459998075923,
"count": 10,
"is_parallel": true,
"self": 0.0018693459998075923
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 307.89248383600125,
"count": 18202,
"is_parallel": true,
"self": 12.643340059992056,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.548435339998491,
"count": 18202,
"is_parallel": true,
"self": 6.548435339998491
},
"communicator.exchange": {
"total": 244.76414606400988,
"count": 18202,
"is_parallel": true,
"self": 244.76414606400988
},
"steps_from_proto": {
"total": 43.93656237200082,
"count": 18202,
"is_parallel": true,
"self": 8.638896064047799,
"children": {
"_process_rank_one_or_two_observation": {
"total": 35.29766630795302,
"count": 182020,
"is_parallel": true,
"self": 35.29766630795302
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.000120783999818741,
"count": 1,
"self": 0.000120783999818741,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 560.0659626420123,
"count": 540788,
"is_parallel": true,
"self": 12.915708010987828,
"children": {
"process_trajectory": {
"total": 310.2455795760245,
"count": 540788,
"is_parallel": true,
"self": 308.1869526850245,
"children": {
"RLTrainer._checkpoint": {
"total": 2.058626891000017,
"count": 4,
"is_parallel": true,
"self": 2.058626891000017
}
}
},
"_update_policy": {
"total": 236.90467505499998,
"count": 90,
"is_parallel": true,
"self": 93.58356092100075,
"children": {
"TorchPPOOptimizer.update": {
"total": 143.32111413399923,
"count": 4584,
"is_parallel": true,
"self": 143.32111413399923
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1580008830001134,
"count": 1,
"self": 0.0009631230000195501,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15703776000009384,
"count": 1,
"self": 0.15703776000009384
}
}
}
}
}
}
}