ITSheep's picture
First Push
e0b9a5e verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.1006966829299927,
"min": 1.1006966829299927,
"max": 2.870684862136841,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10509.4521484375,
"min": 10509.4521484375,
"max": 29461.83984375,
"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": 11.948827743530273,
"min": 0.39993056654930115,
"max": 11.948827743530273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2330.021484375,
"min": 77.58653259277344,
"max": 2430.15966796875,
"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": 0.06897342760417172,
"min": 0.06063493012779338,
"max": 0.07619074494440985,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27589371041668687,
"min": 0.24956559790207036,
"max": 0.38095372472204925,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2081717186260457,
"min": 0.13231613481526866,
"max": 0.27960435973078596,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8326868745041828,
"min": 0.5292645392610746,
"max": 1.3683872792650673,
"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": 23.522727272727273,
"min": 3.5681818181818183,
"max": 23.581818181818182,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1035.0,
"min": 157.0,
"max": 1297.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.522727272727273,
"min": 3.5681818181818183,
"max": 23.581818181818182,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1035.0,
"min": 157.0,
"max": 1297.0,
"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": "1734961179",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1734961779"
},
"total": 600.624108767,
"count": 1,
"self": 0.8224124589999064,
"children": {
"run_training.setup": {
"total": 0.07362578500004702,
"count": 1,
"self": 0.07362578500004702
},
"TrainerController.start_learning": {
"total": 599.728070523,
"count": 1,
"self": 0.8598886279947919,
"children": {
"TrainerController._reset_env": {
"total": 6.250205628999993,
"count": 1,
"self": 6.250205628999993
},
"TrainerController.advance": {
"total": 592.5310325770052,
"count": 18202,
"self": 0.42699774900461307,
"children": {
"env_step": {
"total": 592.1040348280006,
"count": 18202,
"self": 452.2421730680007,
"children": {
"SubprocessEnvManager._take_step": {
"total": 139.4362938149916,
"count": 18202,
"self": 2.3998648539976557,
"children": {
"TorchPolicy.evaluate": {
"total": 137.03642896099393,
"count": 18202,
"self": 137.03642896099393
}
}
},
"workers": {
"total": 0.4255679450083676,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 597.718651319996,
"count": 18202,
"is_parallel": true,
"self": 287.5528761339933,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003436460999978408,
"count": 1,
"is_parallel": true,
"self": 0.0010421500001029926,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0023943109998754153,
"count": 10,
"is_parallel": true,
"self": 0.0023943109998754153
}
}
},
"UnityEnvironment.step": {
"total": 0.04271425599995382,
"count": 1,
"is_parallel": true,
"self": 0.0008192729999905168,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004515069999797561,
"count": 1,
"is_parallel": true,
"self": 0.0004515069999797561
},
"communicator.exchange": {
"total": 0.03898409700002503,
"count": 1,
"is_parallel": true,
"self": 0.03898409700002503
},
"steps_from_proto": {
"total": 0.002459378999958517,
"count": 1,
"is_parallel": true,
"self": 0.0004890409999802614,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019703379999782555,
"count": 10,
"is_parallel": true,
"self": 0.0019703379999782555
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 310.16577518600263,
"count": 18201,
"is_parallel": true,
"self": 14.80235255199807,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.653672099992832,
"count": 18201,
"is_parallel": true,
"self": 7.653672099992832
},
"communicator.exchange": {
"total": 243.1602121490062,
"count": 18201,
"is_parallel": true,
"self": 243.1602121490062
},
"steps_from_proto": {
"total": 44.54953838500552,
"count": 18201,
"is_parallel": true,
"self": 8.738806435978063,
"children": {
"_process_rank_one_or_two_observation": {
"total": 35.810731949027456,
"count": 182010,
"is_parallel": true,
"self": 35.810731949027456
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.000137425000048097,
"count": 1,
"self": 0.000137425000048097,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 585.8677342579871,
"count": 779566,
"is_parallel": true,
"self": 17.3782151989393,
"children": {
"process_trajectory": {
"total": 313.5981566260476,
"count": 779566,
"is_parallel": true,
"self": 312.8044823100478,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7936743159998514,
"count": 4,
"is_parallel": true,
"self": 0.7936743159998514
}
}
},
"_update_policy": {
"total": 254.8913624330001,
"count": 90,
"is_parallel": true,
"self": 71.52590728100347,
"children": {
"TorchPPOOptimizer.update": {
"total": 183.36545515199663,
"count": 4587,
"is_parallel": true,
"self": 183.36545515199663
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08680626399996072,
"count": 1,
"self": 0.0016016579997994995,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08520460600016122,
"count": 1,
"self": 0.08520460600016122
}
}
}
}
}
}
}