MRNH's picture
First Push
c00cb71
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9844964742660522,
"min": 0.9844964742660522,
"max": 2.8472604751586914,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9410.8017578125,
"min": 9410.8017578125,
"max": 29190.11328125,
"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": 13.04745864868164,
"min": 0.37685221433639526,
"max": 13.04745864868164,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2544.25439453125,
"min": 73.10932922363281,
"max": 2628.4970703125,
"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": 0.10154991122861462,
"min": 0.09444244847077832,
"max": 0.10154991122861462,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.4061996449144585,
"min": 0.38442003346392406,
"max": 0.49886754743826767,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1777778241564246,
"min": 0.12241374966265126,
"max": 0.2528366092723959,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7111112966256984,
"min": 0.489654998650605,
"max": 1.2641830463619794,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000007e-06,
"min": 8.082097306000007e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400003e-05,
"min": 3.232838922400003e-05,
"max": 0.0013851600382799997,
"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": 0.9617200000000001,
"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": 25.977272727272727,
"min": 3.659090909090909,
"max": 25.977272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1143.0,
"min": 161.0,
"max": 1397.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.977272727272727,
"min": 3.659090909090909,
"max": 25.977272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1143.0,
"min": 161.0,
"max": 1397.0,
"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": "1691748212",
"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": "1691748825"
},
"total": 613.029406629,
"count": 1,
"self": 0.43627205100005995,
"children": {
"run_training.setup": {
"total": 0.04325950399999101,
"count": 1,
"self": 0.04325950399999101
},
"TrainerController.start_learning": {
"total": 612.549875074,
"count": 1,
"self": 0.5484349390013676,
"children": {
"TrainerController._reset_env": {
"total": 4.266169681000008,
"count": 1,
"self": 4.266169681000008
},
"TrainerController.advance": {
"total": 607.5779083789987,
"count": 18202,
"self": 0.26895082299574824,
"children": {
"env_step": {
"total": 607.308957556003,
"count": 18202,
"self": 488.32574421501226,
"children": {
"SubprocessEnvManager._take_step": {
"total": 118.71247724399353,
"count": 18202,
"self": 1.6701011009974422,
"children": {
"TorchPolicy.evaluate": {
"total": 117.04237614299609,
"count": 18202,
"self": 117.04237614299609
}
}
},
"workers": {
"total": 0.2707360969971546,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 610.9993444319953,
"count": 18202,
"is_parallel": true,
"self": 363.01224674100604,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00562092699999539,
"count": 1,
"is_parallel": true,
"self": 0.004187472000012349,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014334549999830415,
"count": 10,
"is_parallel": true,
"self": 0.0014334549999830415
}
}
},
"UnityEnvironment.step": {
"total": 0.03841047100002015,
"count": 1,
"is_parallel": true,
"self": 0.0006454360000134329,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040141900001344766,
"count": 1,
"is_parallel": true,
"self": 0.00040141900001344766
},
"communicator.exchange": {
"total": 0.035280258999989655,
"count": 1,
"is_parallel": true,
"self": 0.035280258999989655
},
"steps_from_proto": {
"total": 0.002083357000003616,
"count": 1,
"is_parallel": true,
"self": 0.00036280399996257984,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017205530000410363,
"count": 10,
"is_parallel": true,
"self": 0.0017205530000410363
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 247.98709769098923,
"count": 18201,
"is_parallel": true,
"self": 10.477949641993746,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.344192769991935,
"count": 18201,
"is_parallel": true,
"self": 5.344192769991935
},
"communicator.exchange": {
"total": 196.22703911599967,
"count": 18201,
"is_parallel": true,
"self": 196.22703911599967
},
"steps_from_proto": {
"total": 35.93791616300388,
"count": 18201,
"is_parallel": true,
"self": 6.476857442994628,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.461058720009248,
"count": 182010,
"is_parallel": true,
"self": 29.461058720009248
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012877300002855918,
"count": 1,
"self": 0.00012877300002855918,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 604.0299458470172,
"count": 427910,
"is_parallel": true,
"self": 9.628732653039492,
"children": {
"process_trajectory": {
"total": 253.34229799897776,
"count": 427910,
"is_parallel": true,
"self": 252.48753691297787,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8547610859998827,
"count": 4,
"is_parallel": true,
"self": 0.8547610859998827
}
}
},
"_update_policy": {
"total": 341.05891519499994,
"count": 90,
"is_parallel": true,
"self": 112.53401863900035,
"children": {
"TorchPPOOptimizer.update": {
"total": 228.5248965559996,
"count": 15295,
"is_parallel": true,
"self": 228.5248965559996
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.15723330199989505,
"count": 1,
"self": 0.0011275199999545293,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15610578199994052,
"count": 1,
"self": 0.15610578199994052
}
}
}
}
}
}
}