mpetrikov's picture
First Push
add86f8
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8181692361831665,
"min": 0.8181692361831665,
"max": 2.8684566020965576,
"count": 30
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8369.87109375,
"min": 8281.375,
"max": 29407.41796875,
"count": 30
},
"SnowballTarget.Step.mean": {
"value": 299968.0,
"min": 9952.0,
"max": 299968.0,
"count": 30
},
"SnowballTarget.Step.sum": {
"value": 299968.0,
"min": 9952.0,
"max": 299968.0,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.062841415405273,
"min": 0.2617315649986267,
"max": 13.199756622314453,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2664.819580078125,
"min": 50.77592086791992,
"max": 2705.9501953125,
"count": 30
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 30
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 30
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06999272988271996,
"min": 0.06303657197899085,
"max": 0.07555180017106086,
"count": 30
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.34996364941359975,
"min": 0.2521462879159634,
"max": 0.369776627911693,
"count": 30
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1889498771697867,
"min": 0.10937821510357454,
"max": 0.28730711808391646,
"count": 30
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9447493858489335,
"min": 0.43751286041429815,
"max": 1.3134163913189196,
"count": 30
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 5.288098237333331e-06,
"min": 5.288098237333331e-06,
"max": 0.00029458800180399996,
"count": 30
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 2.6440491186666655e-05,
"min": 2.6440491186666655e-05,
"max": 0.0014234400255199997,
"count": 30
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10176266666666667,
"min": 0.10176266666666667,
"max": 0.198196,
"count": 30
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5088133333333333,
"min": 0.42025066666666666,
"max": 0.97448,
"count": 30
},
"SnowballTarget.Policy.Beta.mean": {
"value": 9.795706666666662e-05,
"min": 9.795706666666662e-05,
"max": 0.0049099804000000006,
"count": 30
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0004897853333333331,
"min": 0.0004897853333333331,
"max": 0.023726551999999998,
"count": 30
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.745454545454546,
"min": 2.8636363636363638,
"max": 25.87272727272727,
"count": 30
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1416.0,
"min": 126.0,
"max": 1423.0,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.745454545454546,
"min": 2.8636363636363638,
"max": 25.87272727272727,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1416.0,
"min": 126.0,
"max": 1423.0,
"count": 30
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 30
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 30
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1688772070",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"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": "1688772787"
},
"total": 717.0955925420001,
"count": 1,
"self": 0.43603485700020883,
"children": {
"run_training.setup": {
"total": 0.043431040999962534,
"count": 1,
"self": 0.043431040999962534
},
"TrainerController.start_learning": {
"total": 716.6161266439999,
"count": 1,
"self": 0.8472846520056692,
"children": {
"TrainerController._reset_env": {
"total": 4.651252976000023,
"count": 1,
"self": 4.651252976000023
},
"TrainerController.advance": {
"total": 710.9867781859942,
"count": 27333,
"self": 0.41235011197977656,
"children": {
"env_step": {
"total": 710.5744280740145,
"count": 27333,
"self": 519.159006932025,
"children": {
"SubprocessEnvManager._take_step": {
"total": 191.00228552198985,
"count": 27333,
"self": 2.6213036099882174,
"children": {
"TorchPolicy.evaluate": {
"total": 188.38098191200163,
"count": 27333,
"self": 188.38098191200163
}
}
},
"workers": {
"total": 0.4131356199995935,
"count": 27333,
"self": 0.0,
"children": {
"worker_root": {
"total": 714.1404469009872,
"count": 27333,
"is_parallel": true,
"self": 334.6947869019814,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006032156999935978,
"count": 1,
"is_parallel": true,
"self": 0.004386374999853615,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001645782000082363,
"count": 10,
"is_parallel": true,
"self": 0.001645782000082363
}
}
},
"UnityEnvironment.step": {
"total": 0.07718578699996215,
"count": 1,
"is_parallel": true,
"self": 0.011234482999952888,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003988680000475142,
"count": 1,
"is_parallel": true,
"self": 0.0003988680000475142
},
"communicator.exchange": {
"total": 0.0629796539999461,
"count": 1,
"is_parallel": true,
"self": 0.0629796539999461
},
"steps_from_proto": {
"total": 0.00257278200001565,
"count": 1,
"is_parallel": true,
"self": 0.0005738029999520222,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019989790000636276,
"count": 10,
"is_parallel": true,
"self": 0.0019989790000636276
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 379.4456599990058,
"count": 27332,
"is_parallel": true,
"self": 15.776268615049503,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.965639185989062,
"count": 27332,
"is_parallel": true,
"self": 7.965639185989062
},
"communicator.exchange": {
"total": 302.03982753898254,
"count": 27332,
"is_parallel": true,
"self": 302.03982753898254
},
"steps_from_proto": {
"total": 53.66392465898468,
"count": 27332,
"is_parallel": true,
"self": 9.529856512960805,
"children": {
"_process_rank_one_or_two_observation": {
"total": 44.13406814602388,
"count": 273320,
"is_parallel": true,
"self": 44.13406814602388
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00041744200007087784,
"count": 1,
"self": 0.00041744200007087784,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 705.4046177569265,
"count": 688758,
"is_parallel": true,
"self": 15.174187537050102,
"children": {
"process_trajectory": {
"total": 386.2734424628778,
"count": 688758,
"is_parallel": true,
"self": 384.778110160878,
"children": {
"RLTrainer._checkpoint": {
"total": 1.495332301999838,
"count": 6,
"is_parallel": true,
"self": 1.495332301999838
}
}
},
"_update_policy": {
"total": 303.9569877569986,
"count": 136,
"is_parallel": true,
"self": 120.18728258301405,
"children": {
"TorchPPOOptimizer.update": {
"total": 183.76970517398456,
"count": 6933,
"is_parallel": true,
"self": 183.76970517398456
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1303933879999022,
"count": 1,
"self": 0.0006699339999158838,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1297234539999863,
"count": 1,
"self": 0.1297234539999863
}
}
}
}
}
}
}