mazeinmouse's picture
First Push
5ac5ae8
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9078014492988586,
"min": 0.9078014492988586,
"max": 2.8602139949798584,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8677.673828125,
"min": 8677.673828125,
"max": 29480.2265625,
"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": 12.810604095458984,
"min": 0.22948208451271057,
"max": 12.810604095458984,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2498.06787109375,
"min": 44.51952362060547,
"max": 2604.58203125,
"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": 0.06937076113364823,
"min": 0.06310713291938608,
"max": 0.07478065593670323,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27748304453459294,
"min": 0.2524285316775443,
"max": 0.37390327968351617,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20575837301565153,
"min": 0.11600501161906411,
"max": 0.2827115444576039,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8230334920626061,
"min": 0.46402004647625644,
"max": 1.4135577222880193,
"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": 24.863636363636363,
"min": 3.25,
"max": 25.254545454545454,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1094.0,
"min": 143.0,
"max": 1389.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.863636363636363,
"min": 3.25,
"max": 25.254545454545454,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1094.0,
"min": 143.0,
"max": 1389.0,
"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": "1688427239",
"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": "1688427687"
},
"total": 448.244843049,
"count": 1,
"self": 0.3830546389999654,
"children": {
"run_training.setup": {
"total": 0.040705945000013344,
"count": 1,
"self": 0.040705945000013344
},
"TrainerController.start_learning": {
"total": 447.821082465,
"count": 1,
"self": 0.4770429539981933,
"children": {
"TrainerController._reset_env": {
"total": 3.996340745999987,
"count": 1,
"self": 3.996340745999987
},
"TrainerController.advance": {
"total": 443.2072440390017,
"count": 18203,
"self": 0.23526389800520064,
"children": {
"env_step": {
"total": 442.9719801409965,
"count": 18203,
"self": 322.8009258949828,
"children": {
"SubprocessEnvManager._take_step": {
"total": 119.9326262600099,
"count": 18203,
"self": 1.6572573100082764,
"children": {
"TorchPolicy.evaluate": {
"total": 118.27536895000162,
"count": 18203,
"self": 118.27536895000162
}
}
},
"workers": {
"total": 0.238427986003785,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 446.24085424800353,
"count": 18203,
"is_parallel": true,
"self": 210.12685050499567,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005447069999945597,
"count": 1,
"is_parallel": true,
"self": 0.003953739999928985,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014933300000166128,
"count": 10,
"is_parallel": true,
"self": 0.0014933300000166128
}
}
},
"UnityEnvironment.step": {
"total": 0.0439196570000604,
"count": 1,
"is_parallel": true,
"self": 0.0006405190000577932,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040936899995358544,
"count": 1,
"is_parallel": true,
"self": 0.00040936899995358544
},
"communicator.exchange": {
"total": 0.04073610299997199,
"count": 1,
"is_parallel": true,
"self": 0.04073610299997199
},
"steps_from_proto": {
"total": 0.002133666000077028,
"count": 1,
"is_parallel": true,
"self": 0.00038023700005851424,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017534290000185138,
"count": 10,
"is_parallel": true,
"self": 0.0017534290000185138
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 236.11400374300786,
"count": 18202,
"is_parallel": true,
"self": 10.010549744989248,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.051355255012481,
"count": 18202,
"is_parallel": true,
"self": 5.051355255012481
},
"communicator.exchange": {
"total": 187.98323231100346,
"count": 18202,
"is_parallel": true,
"self": 187.98323231100346
},
"steps_from_proto": {
"total": 33.068866432002665,
"count": 18202,
"is_parallel": true,
"self": 5.822839118979687,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.246027313022978,
"count": 182020,
"is_parallel": true,
"self": 27.246027313022978
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011415700009820284,
"count": 1,
"self": 0.00011415700009820284,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 439.90528292804095,
"count": 414251,
"is_parallel": true,
"self": 9.138084517016864,
"children": {
"process_trajectory": {
"total": 239.69528292902396,
"count": 414251,
"is_parallel": true,
"self": 238.7023856500242,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9928972789997488,
"count": 4,
"is_parallel": true,
"self": 0.9928972789997488
}
}
},
"_update_policy": {
"total": 191.07191548200012,
"count": 90,
"is_parallel": true,
"self": 74.39761430199894,
"children": {
"TorchPPOOptimizer.update": {
"total": 116.67430118000118,
"count": 4587,
"is_parallel": true,
"self": 116.67430118000118
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14034056900004543,
"count": 1,
"self": 0.0008862879999469442,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1394542810000985,
"count": 1,
"self": 0.1394542810000985
}
}
}
}
}
}
}