archiMAD's picture
First training of SnowballTarget
e20399e verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.963749349117279,
"min": 0.963749349117279,
"max": 2.870985507965088,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9233.6826171875,
"min": 9233.6826171875,
"max": 29401.763671875,
"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": 12.80349063873291,
"min": 0.4775376319885254,
"max": 12.83475112915039,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2496.6806640625,
"min": 92.64230346679688,
"max": 2618.289306640625,
"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": 0.06813438108019909,
"min": 0.05954917305429905,
"max": 0.07199738858017715,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27253752432079636,
"min": 0.2381966922171962,
"max": 0.3540379753166253,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1982062465566046,
"min": 0.1328108971904251,
"max": 0.2921658360636702,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7928249862264184,
"min": 0.5312435887617004,
"max": 1.3950335374649834,
"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": 24.681818181818183,
"min": 3.477272727272727,
"max": 25.75,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1086.0,
"min": 153.0,
"max": 1400.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.681818181818183,
"min": 3.477272727272727,
"max": 25.75,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1086.0,
"min": 153.0,
"max": 1400.0,
"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": "1708793566",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1708794221"
},
"total": 655.381558067,
"count": 1,
"self": 0.5926735099999405,
"children": {
"run_training.setup": {
"total": 0.07487801800004945,
"count": 1,
"self": 0.07487801800004945
},
"TrainerController.start_learning": {
"total": 654.714006539,
"count": 1,
"self": 1.0696073550035408,
"children": {
"TrainerController._reset_env": {
"total": 4.683220229999961,
"count": 1,
"self": 4.683220229999961
},
"TrainerController.advance": {
"total": 648.8581786059965,
"count": 18203,
"self": 0.4969109429988521,
"children": {
"env_step": {
"total": 648.3612676629976,
"count": 18203,
"self": 500.2592383199849,
"children": {
"SubprocessEnvManager._take_step": {
"total": 147.62369098999636,
"count": 18203,
"self": 3.0893289620098585,
"children": {
"TorchPolicy.evaluate": {
"total": 144.5343620279865,
"count": 18203,
"self": 144.5343620279865
}
}
},
"workers": {
"total": 0.4783383530163974,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 652.3090360760025,
"count": 18203,
"is_parallel": true,
"self": 297.48470047400315,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007032120999951985,
"count": 1,
"is_parallel": true,
"self": 0.004588162000004559,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0024439589999474265,
"count": 10,
"is_parallel": true,
"self": 0.0024439589999474265
}
}
},
"UnityEnvironment.step": {
"total": 0.05502703299998757,
"count": 1,
"is_parallel": true,
"self": 0.0008512199999586301,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005197460000090359,
"count": 1,
"is_parallel": true,
"self": 0.0005197460000090359
},
"communicator.exchange": {
"total": 0.04635040100004062,
"count": 1,
"is_parallel": true,
"self": 0.04635040100004062
},
"steps_from_proto": {
"total": 0.007305665999979283,
"count": 1,
"is_parallel": true,
"self": 0.0006063789998052016,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.006699287000174081,
"count": 10,
"is_parallel": true,
"self": 0.006699287000174081
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 354.82433560199934,
"count": 18202,
"is_parallel": true,
"self": 17.28553719600677,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.737896416998865,
"count": 18202,
"is_parallel": true,
"self": 8.737896416998865
},
"communicator.exchange": {
"total": 279.1835058869932,
"count": 18202,
"is_parallel": true,
"self": 279.1835058869932
},
"steps_from_proto": {
"total": 49.6173961020005,
"count": 18202,
"is_parallel": true,
"self": 10.246319075038059,
"children": {
"_process_rank_one_or_two_observation": {
"total": 39.37107702696244,
"count": 182020,
"is_parallel": true,
"self": 39.37107702696244
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00023487199996452546,
"count": 1,
"self": 0.00023487199996452546,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 641.0884458949482,
"count": 875431,
"is_parallel": true,
"self": 20.596166714022843,
"children": {
"process_trajectory": {
"total": 357.35360478992584,
"count": 875431,
"is_parallel": true,
"self": 356.4023522349263,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9512525549995416,
"count": 4,
"is_parallel": true,
"self": 0.9512525549995416
}
}
},
"_update_policy": {
"total": 263.13867439099954,
"count": 90,
"is_parallel": true,
"self": 68.90366126800677,
"children": {
"TorchPPOOptimizer.update": {
"total": 194.23501312299277,
"count": 4587,
"is_parallel": true,
"self": 194.23501312299277
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1027654760000587,
"count": 1,
"self": 0.001459319000105097,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1013061569999536,
"count": 1,
"self": 0.1013061569999536
}
}
}
}
}
}
}