silver4444's picture
FirstPush
97b3149 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.6878721117973328,
"min": 0.6257317662239075,
"max": 2.6808388233184814,
"count": 16
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 21186.4609375,
"min": 18391.5078125,
"max": 80446.609375,
"count": 16
},
"SnowballTarget.Step.mean": {
"value": 479984.0,
"min": 29880.0,
"max": 479984.0,
"count": 16
},
"SnowballTarget.Step.sum": {
"value": 479984.0,
"min": 29880.0,
"max": 479984.0,
"count": 16
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.46582317352295,
"min": 1.7410210371017456,
"max": 13.539365768432617,
"count": 16
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 4066.6787109375,
"min": 515.3422241210938,
"max": 4066.6787109375,
"count": 16
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 16
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 30646.0,
"min": 28457.0,
"max": 30646.0,
"count": 16
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.350649350649352,
"min": 6.321678321678322,
"max": 26.541095890410958,
"count": 16
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 4058.0,
"min": 904.0,
"max": 4060.0,
"count": 16
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.350649350649352,
"min": 6.321678321678322,
"max": 26.541095890410958,
"count": 16
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 4058.0,
"min": 904.0,
"max": 4060.0,
"count": 16
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.030718824454483446,
"min": 0.02769466082670708,
"max": 0.03351625200396354,
"count": 16
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.4300635423627682,
"min": 0.36003059074719207,
"max": 0.46922752805548956,
"count": 16
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20684371782200678,
"min": 0.19910646847316196,
"max": 0.3086138748164688,
"count": 16
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 2.895812049508095,
"min": 2.708884124457836,
"max": 4.320594247430563,
"count": 16
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 2.082009306e-05,
"min": 2.082009306e-05,
"max": 0.0002907600030799999,
"count": 16
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.00029148130284,
"min": 0.00029148130284,
"max": 0.0038211601262799996,
"count": 16
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10694,
"min": 0.10694,
"max": 0.19692,
"count": 16
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 1.4971599999999998,
"min": 1.4971599999999998,
"max": 2.67372,
"count": 16
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.000356306,
"min": 0.000356306,
"max": 0.004846308,
"count": 16
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.004988284,
"min": 0.004988284,
"max": 0.063698628,
"count": 16
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 16
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 16
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1767578712",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1767579852"
},
"total": 1140.9203021450003,
"count": 1,
"self": 0.43166880000035235,
"children": {
"run_training.setup": {
"total": 0.027309306000006472,
"count": 1,
"self": 0.027309306000006472
},
"TrainerController.start_learning": {
"total": 1140.461324039,
"count": 1,
"self": 1.1290509970149287,
"children": {
"TrainerController._reset_env": {
"total": 2.791906116999826,
"count": 1,
"self": 2.791906116999826
},
"TrainerController.advance": {
"total": 1136.4613691249854,
"count": 45528,
"self": 1.1465885320124016,
"children": {
"env_step": {
"total": 853.352400175967,
"count": 45528,
"self": 667.7625598139512,
"children": {
"SubprocessEnvManager._take_step": {
"total": 184.92297451104923,
"count": 45528,
"self": 3.423870183002691,
"children": {
"TorchPolicy.evaluate": {
"total": 181.49910432804654,
"count": 45528,
"self": 181.49910432804654
}
}
},
"workers": {
"total": 0.6668658509665875,
"count": 45528,
"self": 0.0,
"children": {
"worker_root": {
"total": 1136.2893909148986,
"count": 45528,
"is_parallel": true,
"self": 552.2142218399024,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005047801000046093,
"count": 1,
"is_parallel": true,
"self": 0.0034684530000959057,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001579347999950187,
"count": 10,
"is_parallel": true,
"self": 0.001579347999950187
}
}
},
"UnityEnvironment.step": {
"total": 0.0367572539998946,
"count": 1,
"is_parallel": true,
"self": 0.0006638249997195089,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003803980000611773,
"count": 1,
"is_parallel": true,
"self": 0.0003803980000611773
},
"communicator.exchange": {
"total": 0.033803010000156064,
"count": 1,
"is_parallel": true,
"self": 0.033803010000156064
},
"steps_from_proto": {
"total": 0.001910020999957851,
"count": 1,
"is_parallel": true,
"self": 0.00040300599994225195,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001507015000015599,
"count": 10,
"is_parallel": true,
"self": 0.001507015000015599
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 584.0751690749962,
"count": 45527,
"is_parallel": true,
"self": 27.015423736048206,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 14.35794822698972,
"count": 45527,
"is_parallel": true,
"self": 14.35794822698972
},
"communicator.exchange": {
"total": 445.7128775830156,
"count": 45527,
"is_parallel": true,
"self": 445.7128775830156
},
"steps_from_proto": {
"total": 96.98891952894269,
"count": 45527,
"is_parallel": true,
"self": 17.71998362769409,
"children": {
"_process_rank_one_or_two_observation": {
"total": 79.2689359012486,
"count": 455270,
"is_parallel": true,
"self": 79.2689359012486
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 281.962380417006,
"count": 45528,
"self": 1.48407251794265,
"children": {
"process_trajectory": {
"total": 55.49099461706123,
"count": 45528,
"self": 54.61774535106065,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8732492660005846,
"count": 10,
"self": 0.8732492660005846
}
}
},
"_update_policy": {
"total": 224.9873132820021,
"count": 227,
"self": 156.1017639820011,
"children": {
"TorchPPOOptimizer.update": {
"total": 68.885549300001,
"count": 4540,
"self": 68.885549300001
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0019998626376037e-06,
"count": 1,
"self": 1.0019998626376037e-06
},
"TrainerController._save_models": {
"total": 0.07899679799993464,
"count": 1,
"self": 0.00076503899981617,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07823175900011847,
"count": 1,
"self": 0.07823175900011847
}
}
}
}
}
}
}