Ellipsoul's picture
First Push
dae38c9
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.948182225227356,
"min": 0.948182225227356,
"max": 2.8737854957580566,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9053.244140625,
"min": 9053.244140625,
"max": 29462.048828125,
"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": 12.353062629699707,
"min": 0.4557296931743622,
"max": 12.353062629699707,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2408.84716796875,
"min": 88.41156005859375,
"max": 2496.4169921875,
"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": 0.0729312405208154,
"min": 0.06472679365719622,
"max": 0.07492705745700697,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2917249620832616,
"min": 0.2589071746287849,
"max": 0.35519124979870026,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19403249222566102,
"min": 0.10659457669894704,
"max": 0.2772628878261528,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7761299689026441,
"min": 0.42637830679578814,
"max": 1.3863144391307642,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 6.735097306000005e-06,
"min": 6.735097306000005e-06,
"max": 0.000243235002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 2.694038922400002e-05,
"min": 2.694038922400002e-05,
"max": 0.00115430003828,
"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": 24.227272727272727,
"min": 2.909090909090909,
"max": 24.4,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1066.0,
"min": 128.0,
"max": 1342.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.227272727272727,
"min": 2.909090909090909,
"max": 24.4,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1066.0,
"min": 128.0,
"max": 1342.0,
"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": "1679605109",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1679605612"
},
"total": 502.934969337,
"count": 1,
"self": 0.3846615879999149,
"children": {
"run_training.setup": {
"total": 0.10894101600001704,
"count": 1,
"self": 0.10894101600001704
},
"TrainerController.start_learning": {
"total": 502.44136673300005,
"count": 1,
"self": 0.5786568190067101,
"children": {
"TrainerController._reset_env": {
"total": 10.214403532000006,
"count": 1,
"self": 10.214403532000006
},
"TrainerController.advance": {
"total": 491.5042816479933,
"count": 18203,
"self": 0.30633983799674525,
"children": {
"env_step": {
"total": 491.19794180999656,
"count": 18203,
"self": 354.66444419599884,
"children": {
"SubprocessEnvManager._take_step": {
"total": 136.23938653599828,
"count": 18203,
"self": 2.461685731996681,
"children": {
"TorchPolicy.evaluate": {
"total": 133.7777008040016,
"count": 18203,
"self": 133.7777008040016
}
}
},
"workers": {
"total": 0.294111077999446,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 500.6459202559956,
"count": 18203,
"is_parallel": true,
"self": 239.34662968999714,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005056113000023288,
"count": 1,
"is_parallel": true,
"self": 0.003367567000168492,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016885459998547958,
"count": 10,
"is_parallel": true,
"self": 0.0016885459998547958
}
}
},
"UnityEnvironment.step": {
"total": 0.0512409599999728,
"count": 1,
"is_parallel": true,
"self": 0.0006686420000505677,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003259719999846311,
"count": 1,
"is_parallel": true,
"self": 0.0003259719999846311
},
"communicator.exchange": {
"total": 0.04870778699995526,
"count": 1,
"is_parallel": true,
"self": 0.04870778699995526
},
"steps_from_proto": {
"total": 0.0015385589999823424,
"count": 1,
"is_parallel": true,
"self": 0.00033478799986141894,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012037710001209234,
"count": 10,
"is_parallel": true,
"self": 0.0012037710001209234
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 261.29929056599843,
"count": 18202,
"is_parallel": true,
"self": 10.338215277996312,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.6932278930001985,
"count": 18202,
"is_parallel": true,
"self": 5.6932278930001985
},
"communicator.exchange": {
"total": 210.32923956099194,
"count": 18202,
"is_parallel": true,
"self": 210.32923956099194
},
"steps_from_proto": {
"total": 34.938607834009986,
"count": 18202,
"is_parallel": true,
"self": 6.971503955982598,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.967103878027388,
"count": 182020,
"is_parallel": true,
"self": 27.967103878027388
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001328560000501966,
"count": 1,
"self": 0.0001328560000501966,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 487.5149796789923,
"count": 429271,
"is_parallel": true,
"self": 11.26500315796494,
"children": {
"process_trajectory": {
"total": 271.8455200210273,
"count": 429271,
"is_parallel": true,
"self": 271.0586070760275,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7869129449998127,
"count": 4,
"is_parallel": true,
"self": 0.7869129449998127
}
}
},
"_update_policy": {
"total": 204.40445650000004,
"count": 90,
"is_parallel": true,
"self": 76.23722792900048,
"children": {
"TorchPPOOptimizer.update": {
"total": 128.16722857099955,
"count": 4587,
"is_parallel": true,
"self": 128.16722857099955
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14389187799997671,
"count": 1,
"self": 0.0009235100000068996,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14296836799996981,
"count": 1,
"self": 0.14296836799996981
}
}
}
}
}
}
}