HCho's picture
First Push
8ae0f7d verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0282291173934937,
"min": 1.0282291173934937,
"max": 2.8817696571350098,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9851.462890625,
"min": 9851.462890625,
"max": 29543.90234375,
"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": 12.843191146850586,
"min": 0.20203670859336853,
"max": 12.843191146850586,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2504.42236328125,
"min": 39.19512176513672,
"max": 2599.67431640625,
"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": 0.0674436303002842,
"min": 0.06172179665996273,
"max": 0.07569832973679107,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2697745212011368,
"min": 0.256069305804832,
"max": 0.3600033193277555,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19464181385496082,
"min": 0.08621582311724185,
"max": 0.29223158699916857,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7785672554198433,
"min": 0.3448632924689674,
"max": 1.315448261943518,
"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": 25.363636363636363,
"min": 2.477272727272727,
"max": 25.363636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1116.0,
"min": 109.0,
"max": 1380.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.363636363636363,
"min": 2.477272727272727,
"max": 25.363636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1116.0,
"min": 109.0,
"max": 1380.0,
"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": "1736209746",
"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": "1736210239"
},
"total": 493.2761386750001,
"count": 1,
"self": 0.4894312460000947,
"children": {
"run_training.setup": {
"total": 0.07976876899999752,
"count": 1,
"self": 0.07976876899999752
},
"TrainerController.start_learning": {
"total": 492.70693866,
"count": 1,
"self": 0.6533148539928106,
"children": {
"TrainerController._reset_env": {
"total": 5.362108719000048,
"count": 1,
"self": 5.362108719000048
},
"TrainerController.advance": {
"total": 486.60324515600735,
"count": 18204,
"self": 0.3217648259969792,
"children": {
"env_step": {
"total": 486.28148033001037,
"count": 18204,
"self": 374.2799707540221,
"children": {
"SubprocessEnvManager._take_step": {
"total": 111.68545770798721,
"count": 18204,
"self": 1.5653692779770836,
"children": {
"TorchPolicy.evaluate": {
"total": 110.12008843001013,
"count": 18204,
"self": 110.12008843001013
}
}
},
"workers": {
"total": 0.3160518680010682,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 491.3513908959885,
"count": 18204,
"is_parallel": true,
"self": 236.4080214809867,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002427354000019477,
"count": 1,
"is_parallel": true,
"self": 0.0006690920000664846,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017582619999529925,
"count": 10,
"is_parallel": true,
"self": 0.0017582619999529925
}
}
},
"UnityEnvironment.step": {
"total": 0.043551639999918734,
"count": 1,
"is_parallel": true,
"self": 0.0008303179998847554,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042837400008011173,
"count": 1,
"is_parallel": true,
"self": 0.00042837400008011173
},
"communicator.exchange": {
"total": 0.03993006099995,
"count": 1,
"is_parallel": true,
"self": 0.03993006099995
},
"steps_from_proto": {
"total": 0.002362887000003866,
"count": 1,
"is_parallel": true,
"self": 0.0004290380001066296,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019338489998972364,
"count": 10,
"is_parallel": true,
"self": 0.0019338489998972364
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 254.94336941500183,
"count": 18203,
"is_parallel": true,
"self": 11.662942479984395,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.423718103011424,
"count": 18203,
"is_parallel": true,
"self": 6.423718103011424
},
"communicator.exchange": {
"total": 198.32056514001158,
"count": 18203,
"is_parallel": true,
"self": 198.32056514001158
},
"steps_from_proto": {
"total": 38.536143691994425,
"count": 18203,
"is_parallel": true,
"self": 7.417738727976598,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.118404964017827,
"count": 182030,
"is_parallel": true,
"self": 31.118404964017827
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.151799991333974e-05,
"count": 1,
"self": 7.151799991333974e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 481.141828042965,
"count": 636080,
"is_parallel": true,
"self": 13.773524036934646,
"children": {
"process_trajectory": {
"total": 254.37390072203016,
"count": 636080,
"is_parallel": true,
"self": 253.67317961103015,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7007211110000071,
"count": 4,
"is_parallel": true,
"self": 0.7007211110000071
}
}
},
"_update_policy": {
"total": 212.9944032840002,
"count": 90,
"is_parallel": true,
"self": 67.8167643740054,
"children": {
"TorchPPOOptimizer.update": {
"total": 145.1776389099948,
"count": 4587,
"is_parallel": true,
"self": 145.1776389099948
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08819841299987274,
"count": 1,
"self": 0.0010549460000675026,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08714346699980524,
"count": 1,
"self": 0.08714346699980524
}
}
}
}
}
}
}