jvogie's picture
First Push
14ccf1e
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9393196105957031,
"min": 0.9376823902130127,
"max": 2.8626458644866943,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8958.291015625,
"min": 8958.291015625,
"max": 29347.845703125,
"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": 12.211773872375488,
"min": 0.23489730060100555,
"max": 12.211773872375488,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2381.2958984375,
"min": 45.57007598876953,
"max": 2461.642578125,
"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": 0.06309529110919411,
"min": 0.06309529110919411,
"max": 0.07407177431670396,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25238116443677644,
"min": 0.25238116443677644,
"max": 0.3552147766036868,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21198595738878437,
"min": 0.09559923680681809,
"max": 0.29700833734344034,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8479438295551375,
"min": 0.38239694722727235,
"max": 1.4632439540297377,
"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": 24.522727272727273,
"min": 2.6818181818181817,
"max": 24.522727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1079.0,
"min": 118.0,
"max": 1311.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.522727272727273,
"min": 2.6818181818181817,
"max": 24.522727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1079.0,
"min": 118.0,
"max": 1311.0,
"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": "1698090353",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1698090885"
},
"total": 531.381837761,
"count": 1,
"self": 0.4763947679996363,
"children": {
"run_training.setup": {
"total": 0.08125756700019338,
"count": 1,
"self": 0.08125756700019338
},
"TrainerController.start_learning": {
"total": 530.8241854260002,
"count": 1,
"self": 0.6837574919695726,
"children": {
"TrainerController._reset_env": {
"total": 9.078514120999898,
"count": 1,
"self": 9.078514120999898
},
"TrainerController.advance": {
"total": 520.9732561770309,
"count": 18199,
"self": 0.34418357003642086,
"children": {
"env_step": {
"total": 520.6290726069944,
"count": 18199,
"self": 358.8019945959561,
"children": {
"SubprocessEnvManager._take_step": {
"total": 161.48040065401392,
"count": 18199,
"self": 1.685571969009061,
"children": {
"TorchPolicy.evaluate": {
"total": 159.79482868500486,
"count": 18199,
"self": 159.79482868500486
}
}
},
"workers": {
"total": 0.3466773570244186,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 529.3085478679941,
"count": 18199,
"is_parallel": true,
"self": 258.4171790950004,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0055182690000492585,
"count": 1,
"is_parallel": true,
"self": 0.003908971999635469,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016092970004137896,
"count": 10,
"is_parallel": true,
"self": 0.0016092970004137896
}
}
},
"UnityEnvironment.step": {
"total": 0.07297446300003685,
"count": 1,
"is_parallel": true,
"self": 0.0007782490001773112,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042219700003442995,
"count": 1,
"is_parallel": true,
"self": 0.00042219700003442995
},
"communicator.exchange": {
"total": 0.06523347699999249,
"count": 1,
"is_parallel": true,
"self": 0.06523347699999249
},
"steps_from_proto": {
"total": 0.0065405399998326175,
"count": 1,
"is_parallel": true,
"self": 0.0005242589998033509,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.006016281000029267,
"count": 10,
"is_parallel": true,
"self": 0.006016281000029267
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 270.8913687729937,
"count": 18198,
"is_parallel": true,
"self": 12.060802835076174,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.021142444976704,
"count": 18198,
"is_parallel": true,
"self": 6.021142444976704
},
"communicator.exchange": {
"total": 214.1764878110082,
"count": 18198,
"is_parallel": true,
"self": 214.1764878110082
},
"steps_from_proto": {
"total": 38.63293568193262,
"count": 18198,
"is_parallel": true,
"self": 7.6321045719507765,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.000831109981846,
"count": 181980,
"is_parallel": true,
"self": 31.000831109981846
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012272599997231737,
"count": 1,
"self": 0.00012272599997231737,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 516.4210026980293,
"count": 553000,
"is_parallel": true,
"self": 12.334499261126894,
"children": {
"process_trajectory": {
"total": 291.2886784169036,
"count": 553000,
"is_parallel": true,
"self": 290.4455950259037,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8430833909999365,
"count": 4,
"is_parallel": true,
"self": 0.8430833909999365
}
}
},
"_update_policy": {
"total": 212.79782501999875,
"count": 90,
"is_parallel": true,
"self": 68.03447509900457,
"children": {
"TorchPPOOptimizer.update": {
"total": 144.7633499209942,
"count": 4587,
"is_parallel": true,
"self": 144.7633499209942
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08853490999990754,
"count": 1,
"self": 0.0008718090002730605,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08766310099963448,
"count": 1,
"self": 0.08766310099963448
}
}
}
}
}
}
}