Emperor's picture
First Push
e620a46
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9762689471244812,
"min": 0.9762689471244812,
"max": 2.8629860877990723,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9310.6767578125,
"min": 9310.6767578125,
"max": 29319.83984375,
"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": 13.34732437133789,
"min": 0.3194137215614319,
"max": 13.34732437133789,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2602.728271484375,
"min": 61.96626281738281,
"max": 2691.7734375,
"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": 0.06708294547142407,
"min": 0.06471815032170579,
"max": 0.07416985428580494,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2683317818856963,
"min": 0.2662803790270689,
"max": 0.3708492714290247,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19374261559078504,
"min": 0.129247704274295,
"max": 0.2804022240726387,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7749704623631402,
"min": 0.51699081709718,
"max": 1.3642806343588174,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 2.6940097306000015e-05,
"min": 2.6940097306000015e-05,
"max": 0.000972940002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.00010776038922400006,
"min": 0.00010776038922400006,
"max": 0.004617200038280001,
"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": 26.727272727272727,
"min": 3.3636363636363638,
"max": 26.727272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1176.0,
"min": 148.0,
"max": 1433.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.727272727272727,
"min": 3.3636363636363638,
"max": 26.727272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1176.0,
"min": 148.0,
"max": 1433.0,
"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": "1679253930",
"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": "1679254425"
},
"total": 495.43963263,
"count": 1,
"self": 0.38957190400003583,
"children": {
"run_training.setup": {
"total": 0.1849578549999933,
"count": 1,
"self": 0.1849578549999933
},
"TrainerController.start_learning": {
"total": 494.865102871,
"count": 1,
"self": 0.5529792869976973,
"children": {
"TrainerController._reset_env": {
"total": 8.341498082000044,
"count": 1,
"self": 8.341498082000044
},
"TrainerController.advance": {
"total": 485.81419955100216,
"count": 18200,
"self": 0.306589677994225,
"children": {
"env_step": {
"total": 485.50760987300794,
"count": 18200,
"self": 348.09455442100034,
"children": {
"SubprocessEnvManager._take_step": {
"total": 137.12832195001192,
"count": 18200,
"self": 2.6354983500115168,
"children": {
"TorchPolicy.evaluate": {
"total": 134.4928236000004,
"count": 18200,
"self": 134.4928236000004
}
}
},
"workers": {
"total": 0.2847335019956745,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 493.3316333300023,
"count": 18200,
"is_parallel": true,
"self": 240.58651909900243,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005422103000000789,
"count": 1,
"is_parallel": true,
"self": 0.0038712389999773222,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015508640000234664,
"count": 10,
"is_parallel": true,
"self": 0.0015508640000234664
}
}
},
"UnityEnvironment.step": {
"total": 0.037421750999897085,
"count": 1,
"is_parallel": true,
"self": 0.0003995529998519487,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00032875600004445005,
"count": 1,
"is_parallel": true,
"self": 0.00032875600004445005
},
"communicator.exchange": {
"total": 0.034986516999993,
"count": 1,
"is_parallel": true,
"self": 0.034986516999993
},
"steps_from_proto": {
"total": 0.0017069250000076863,
"count": 1,
"is_parallel": true,
"self": 0.0004013740001482802,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013055509998594061,
"count": 10,
"is_parallel": true,
"self": 0.0013055509998594061
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 252.7451142309999,
"count": 18199,
"is_parallel": true,
"self": 9.951309987009267,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.5737413659953745,
"count": 18199,
"is_parallel": true,
"self": 5.5737413659953745
},
"communicator.exchange": {
"total": 203.1706948799939,
"count": 18199,
"is_parallel": true,
"self": 203.1706948799939
},
"steps_from_proto": {
"total": 34.049367998001344,
"count": 18199,
"is_parallel": true,
"self": 6.80367978000686,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.245688217994484,
"count": 181990,
"is_parallel": true,
"self": 27.245688217994484
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 5.0396999995427905e-05,
"count": 1,
"self": 5.0396999995427905e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 481.9556968809728,
"count": 437192,
"is_parallel": true,
"self": 11.458263654946563,
"children": {
"process_trajectory": {
"total": 269.3674322720266,
"count": 437192,
"is_parallel": true,
"self": 268.5067460470266,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8606862249999949,
"count": 4,
"is_parallel": true,
"self": 0.8606862249999949
}
}
},
"_update_policy": {
"total": 201.13000095399968,
"count": 90,
"is_parallel": true,
"self": 71.20546205499772,
"children": {
"TorchPPOOptimizer.update": {
"total": 129.92453889900196,
"count": 4587,
"is_parallel": true,
"self": 129.92453889900196
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1563755540000784,
"count": 1,
"self": 0.0010418060001029517,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15533374799997546,
"count": 1,
"self": 0.15533374799997546
}
}
}
}
}
}
}