Kittitouch's picture
First Push
5064661
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9528324604034424,
"min": 0.9528324604034424,
"max": 2.861910104751587,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9087.1630859375,
"min": 9087.1630859375,
"max": 29308.8203125,
"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": 12.85693645477295,
"min": 0.37096333503723145,
"max": 12.85693645477295,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2507.1025390625,
"min": 71.96688842773438,
"max": 2615.255126953125,
"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": 0.07285428573064279,
"min": 0.06517588525934044,
"max": 0.07353368914165698,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.29141714292257115,
"min": 0.2671152674319113,
"max": 0.3676684457082849,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20269722162800674,
"min": 0.11229994255186551,
"max": 0.29298095796622486,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.810788886512027,
"min": 0.44919977020746205,
"max": 1.4649047898311243,
"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": 25.59090909090909,
"min": 3.3863636363636362,
"max": 26.068181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1126.0,
"min": 149.0,
"max": 1371.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.59090909090909,
"min": 3.3863636363636362,
"max": 26.068181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1126.0,
"min": 149.0,
"max": 1371.0,
"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": "1678236582",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.22.4",
"end_time_seconds": "1678237034"
},
"total": 451.764913758,
"count": 1,
"self": 0.38776260299999876,
"children": {
"run_training.setup": {
"total": 0.11323026399998071,
"count": 1,
"self": 0.11323026399998071
},
"TrainerController.start_learning": {
"total": 451.263920891,
"count": 1,
"self": 0.5647098779995758,
"children": {
"TrainerController._reset_env": {
"total": 10.185007274999975,
"count": 1,
"self": 10.185007274999975
},
"TrainerController.advance": {
"total": 440.3955112620006,
"count": 18202,
"self": 0.26525631700116037,
"children": {
"env_step": {
"total": 440.1302549449994,
"count": 18202,
"self": 302.5074672959992,
"children": {
"SubprocessEnvManager._take_step": {
"total": 137.35737277199968,
"count": 18202,
"self": 1.6464417570034584,
"children": {
"TorchPolicy.evaluate": {
"total": 135.71093101499622,
"count": 18202,
"self": 29.72319927400008,
"children": {
"TorchPolicy.sample_actions": {
"total": 105.98773174099614,
"count": 18202,
"self": 105.98773174099614
}
}
}
}
},
"workers": {
"total": 0.2654148770005236,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 449.7704318680119,
"count": 18202,
"is_parallel": true,
"self": 220.17679949999882,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0063400989999991,
"count": 1,
"is_parallel": true,
"self": 0.005002617999991799,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013374810000073012,
"count": 10,
"is_parallel": true,
"self": 0.0013374810000073012
}
}
},
"UnityEnvironment.step": {
"total": 0.060740359000021726,
"count": 1,
"is_parallel": true,
"self": 0.00053320300003179,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003823310000257152,
"count": 1,
"is_parallel": true,
"self": 0.0003823310000257152
},
"communicator.exchange": {
"total": 0.05804360499996619,
"count": 1,
"is_parallel": true,
"self": 0.05804360499996619
},
"steps_from_proto": {
"total": 0.0017812199999980294,
"count": 1,
"is_parallel": true,
"self": 0.00041740900007880555,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013638109999192238,
"count": 10,
"is_parallel": true,
"self": 0.0013638109999192238
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 229.59363236801306,
"count": 18201,
"is_parallel": true,
"self": 9.270457668997949,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.029392378998807,
"count": 18201,
"is_parallel": true,
"self": 5.029392378998807
},
"communicator.exchange": {
"total": 185.15100906900716,
"count": 18201,
"is_parallel": true,
"self": 185.15100906900716
},
"steps_from_proto": {
"total": 30.142773251009146,
"count": 18201,
"is_parallel": true,
"self": 6.460017809000874,
"children": {
"_process_rank_one_or_two_observation": {
"total": 23.682755442008272,
"count": 182010,
"is_parallel": true,
"self": 23.682755442008272
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013638999996601342,
"count": 1,
"self": 0.00013638999996601342,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 437.2939830790039,
"count": 388318,
"is_parallel": true,
"self": 9.318909973001894,
"children": {
"process_trajectory": {
"total": 249.75064768700202,
"count": 388318,
"is_parallel": true,
"self": 247.91166994100195,
"children": {
"RLTrainer._checkpoint": {
"total": 1.8389777460000687,
"count": 4,
"is_parallel": true,
"self": 1.8389777460000687
}
}
},
"_update_policy": {
"total": 178.224425419,
"count": 90,
"is_parallel": true,
"self": 64.02228333900234,
"children": {
"TorchPPOOptimizer.update": {
"total": 114.20214207999766,
"count": 4584,
"is_parallel": true,
"self": 114.20214207999766
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11855608599989864,
"count": 1,
"self": 0.0008487599999398299,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11770732599995881,
"count": 1,
"self": 0.11770732599995881
}
}
}
}
}
}
}