RYOBEAR's picture
First Push
fdacffb
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7034497857093811,
"min": 0.6976025700569153,
"max": 2.88728666305542,
"count": 90
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7118.912109375,
"min": 6393.955078125,
"max": 32109.513671875,
"count": 90
},
"SnowballTarget.Step.mean": {
"value": 899928.0,
"min": 9952.0,
"max": 899928.0,
"count": 90
},
"SnowballTarget.Step.sum": {
"value": 899928.0,
"min": 9952.0,
"max": 899928.0,
"count": 90
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.78389835357666,
"min": 0.14133355021476746,
"max": 13.928528785705566,
"count": 90
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1405.9576416015625,
"min": 13.709354400634766,
"max": 1434.638427734375,
"count": 90
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 90
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 13134.0,
"count": 90
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 27.0,
"min": 2.3181818181818183,
"max": 27.727272727272727,
"count": 90
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1485.0,
"min": 102.0,
"max": 1487.0,
"count": 90
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 27.0,
"min": 2.3181818181818183,
"max": 27.727272727272727,
"count": 90
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1485.0,
"min": 102.0,
"max": 1487.0,
"count": 90
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06874647402617162,
"min": 0.0607511452527861,
"max": 0.07715587771057401,
"count": 90
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.13749294805234324,
"min": 0.1215022905055722,
"max": 0.23146763313172203,
"count": 90
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17409881804795826,
"min": 0.07601560772780111,
"max": 0.3074084019495381,
"count": 90
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.34819763609591653,
"min": 0.15203121545560222,
"max": 0.8535028227111874,
"count": 90
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 5.112106000000012e-07,
"min": 5.112106000000012e-07,
"max": 9.926666739999999e-05,
"count": 90
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.0224212000000023e-06,
"min": 1.0224212000000023e-06,
"max": 0.00028826667840000004,
"count": 90
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10051111111111113,
"min": 0.10051111111111113,
"max": 0.1992666666666667,
"count": 90
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.20102222222222227,
"min": 0.20102222222222227,
"max": 0.5882666666666667,
"count": 90
},
"SnowballTarget.Policy.Beta.mean": {
"value": 3.55044444444445e-05,
"min": 3.55044444444445e-05,
"max": 0.004963406666666668,
"count": 90
},
"SnowballTarget.Policy.Beta.sum": {
"value": 7.1008888888889e-05,
"min": 7.1008888888889e-05,
"max": 0.014414506666666665,
"count": 90
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 90
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 90
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1687575823",
"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=SnowballTarget2 --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": "1687577671"
},
"total": 1847.6949618830001,
"count": 1,
"self": 0.2921174170003269,
"children": {
"run_training.setup": {
"total": 0.03749628599996413,
"count": 1,
"self": 0.03749628599996413
},
"TrainerController.start_learning": {
"total": 1847.36534818,
"count": 1,
"self": 2.0489472199999454,
"children": {
"TrainerController._reset_env": {
"total": 3.9043029130000377,
"count": 1,
"self": 3.9043029130000377
},
"TrainerController.advance": {
"total": 1841.2679873029995,
"count": 81936,
"self": 0.9633118169865611,
"children": {
"env_step": {
"total": 1840.304675486013,
"count": 81936,
"self": 1333.0701943800905,
"children": {
"SubprocessEnvManager._take_step": {
"total": 506.28038745394485,
"count": 81936,
"self": 6.191725687951589,
"children": {
"TorchPolicy.evaluate": {
"total": 500.08866176599327,
"count": 81936,
"self": 500.08866176599327
}
}
},
"workers": {
"total": 0.9540936519774732,
"count": 81936,
"self": 0.0,
"children": {
"worker_root": {
"total": 1844.3780067700304,
"count": 81936,
"is_parallel": true,
"self": 1041.3106220910702,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001867215000061151,
"count": 1,
"is_parallel": true,
"self": 0.0005656029999272505,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013016120001339004,
"count": 10,
"is_parallel": true,
"self": 0.0013016120001339004
}
}
},
"UnityEnvironment.step": {
"total": 0.033797909000099935,
"count": 1,
"is_parallel": true,
"self": 0.0005918820000943015,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039498099999946135,
"count": 1,
"is_parallel": true,
"self": 0.00039498099999946135
},
"communicator.exchange": {
"total": 0.03056567700002688,
"count": 1,
"is_parallel": true,
"self": 0.03056567700002688
},
"steps_from_proto": {
"total": 0.0022453689999792914,
"count": 1,
"is_parallel": true,
"self": 0.00039210000034017867,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018532689996391127,
"count": 10,
"is_parallel": true,
"self": 0.0018532689996391127
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 803.0673846789603,
"count": 81935,
"is_parallel": true,
"self": 38.655531934038436,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 19.771051183008808,
"count": 81935,
"is_parallel": true,
"self": 19.771051183008808
},
"communicator.exchange": {
"total": 619.9736982289395,
"count": 81935,
"is_parallel": true,
"self": 619.9736982289395
},
"steps_from_proto": {
"total": 124.66710333297351,
"count": 81935,
"is_parallel": true,
"self": 21.436351150865562,
"children": {
"_process_rank_one_or_two_observation": {
"total": 103.23075218210795,
"count": 819350,
"is_parallel": true,
"self": 103.23075218210795
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0009890740002447274,
"count": 1,
"self": 0.0009890740002447274,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 1837.3454557221967,
"count": 762312,
"is_parallel": true,
"self": 14.722534219202544,
"children": {
"process_trajectory": {
"total": 683.0863609769938,
"count": 762312,
"is_parallel": true,
"self": 679.2227238579939,
"children": {
"RLTrainer._checkpoint": {
"total": 3.863637118999918,
"count": 18,
"is_parallel": true,
"self": 3.863637118999918
}
}
},
"_update_policy": {
"total": 1139.5365605260004,
"count": 204,
"is_parallel": true,
"self": 320.148740854037,
"children": {
"TorchPPOOptimizer.update": {
"total": 819.3878196719634,
"count": 34680,
"is_parallel": true,
"self": 819.3878196719634
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1431216700002551,
"count": 1,
"self": 0.0010047240002677427,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14211694599998737,
"count": 1,
"self": 0.14211694599998737
}
}
}
}
}
}
}