flowerpot76's picture
First Push
3384419
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8652554154396057,
"min": 0.8652554154396057,
"max": 2.8582122325897217,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8280.494140625,
"min": 8280.494140625,
"max": 29239.51171875,
"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": 12.86701488494873,
"min": 0.2125924527645111,
"max": 12.86701488494873,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2509.06787109375,
"min": 41.24293518066406,
"max": 2607.031494140625,
"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": 0.0697570659330642,
"min": 0.06151310389024872,
"max": 0.07557929805845169,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2790282637322568,
"min": 0.24605241556099489,
"max": 0.37789649029225847,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19724242630250313,
"min": 0.10799731604764054,
"max": 0.2885046233149136,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7889697052100125,
"min": 0.43198926419056216,
"max": 1.442523116574568,
"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": 25.295454545454547,
"min": 3.2045454545454546,
"max": 25.295454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1113.0,
"min": 141.0,
"max": 1391.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.295454545454547,
"min": 3.2045454545454546,
"max": 25.295454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1113.0,
"min": 141.0,
"max": 1391.0,
"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": "1682342190",
"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": "1682342643"
},
"total": 452.78981929599996,
"count": 1,
"self": 0.3802703719999272,
"children": {
"run_training.setup": {
"total": 0.17654723300000796,
"count": 1,
"self": 0.17654723300000796
},
"TrainerController.start_learning": {
"total": 452.233001691,
"count": 1,
"self": 0.530481864011108,
"children": {
"TrainerController._reset_env": {
"total": 4.567911693000042,
"count": 1,
"self": 4.567911693000042
},
"TrainerController.advance": {
"total": 447.00890627298884,
"count": 18205,
"self": 0.2798675089898097,
"children": {
"env_step": {
"total": 446.72903876399903,
"count": 18205,
"self": 328.4089508859952,
"children": {
"SubprocessEnvManager._take_step": {
"total": 118.06274628900286,
"count": 18205,
"self": 1.5528615470058753,
"children": {
"TorchPolicy.evaluate": {
"total": 116.50988474199698,
"count": 18205,
"self": 116.50988474199698
}
}
},
"workers": {
"total": 0.2573415890009869,
"count": 18205,
"self": 0.0,
"children": {
"worker_root": {
"total": 450.8649513010007,
"count": 18205,
"is_parallel": true,
"self": 209.29953870899635,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006390426999985266,
"count": 1,
"is_parallel": true,
"self": 0.0040421690001153365,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0023482579998699293,
"count": 10,
"is_parallel": true,
"self": 0.0023482579998699293
}
}
},
"UnityEnvironment.step": {
"total": 0.034828785999991396,
"count": 1,
"is_parallel": true,
"self": 0.000570487999937086,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004041079999979047,
"count": 1,
"is_parallel": true,
"self": 0.0004041079999979047
},
"communicator.exchange": {
"total": 0.03198334500001465,
"count": 1,
"is_parallel": true,
"self": 0.03198334500001465
},
"steps_from_proto": {
"total": 0.0018708450000417542,
"count": 1,
"is_parallel": true,
"self": 0.0003907709998429709,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014800740001987833,
"count": 10,
"is_parallel": true,
"self": 0.0014800740001987833
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 241.56541259200435,
"count": 18204,
"is_parallel": true,
"self": 9.861585716009643,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.3013563809998345,
"count": 18204,
"is_parallel": true,
"self": 5.3013563809998345
},
"communicator.exchange": {
"total": 195.2212611249983,
"count": 18204,
"is_parallel": true,
"self": 195.2212611249983
},
"steps_from_proto": {
"total": 31.181209369996566,
"count": 18204,
"is_parallel": true,
"self": 6.038764855011209,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.142444514985357,
"count": 182040,
"is_parallel": true,
"self": 25.142444514985357
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011062300006869918,
"count": 1,
"self": 0.00011062300006869918,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 443.6312401759571,
"count": 393627,
"is_parallel": true,
"self": 9.970435100971372,
"children": {
"process_trajectory": {
"total": 243.72741867198636,
"count": 393627,
"is_parallel": true,
"self": 242.97280850498635,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7546101670000098,
"count": 4,
"is_parallel": true,
"self": 0.7546101670000098
}
}
},
"_update_policy": {
"total": 189.93338640299936,
"count": 90,
"is_parallel": true,
"self": 70.52953500999604,
"children": {
"TorchPPOOptimizer.update": {
"total": 119.40385139300332,
"count": 4587,
"is_parallel": true,
"self": 119.40385139300332
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12559123799996996,
"count": 1,
"self": 0.0008886360000133209,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12470260199995664,
"count": 1,
"self": 0.12470260199995664
}
}
}
}
}
}
}