OscarGalavizC's picture
First Push
bc3debb verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.1340129375457764,
"min": 1.1340129375457764,
"max": 2.8711886405944824,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10864.9775390625,
"min": 10864.9775390625,
"max": 29435.42578125,
"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": 12.345067024230957,
"min": 0.43371260166168213,
"max": 12.345067024230957,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2407.2880859375,
"min": 84.14024353027344,
"max": 2492.1259765625,
"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": 0.06480488847648981,
"min": 0.06397628198109503,
"max": 0.07619803110890858,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25921955390595924,
"min": 0.25921955390595924,
"max": 0.38099015554454285,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22516338804773256,
"min": 0.14899105719728944,
"max": 0.28503748248605165,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9006535521909302,
"min": 0.5959642287891578,
"max": 1.4251874124302584,
"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": 23.931818181818183,
"min": 3.9318181818181817,
"max": 24.418181818181818,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1053.0,
"min": 173.0,
"max": 1343.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.931818181818183,
"min": 3.9318181818181817,
"max": 24.418181818181818,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1053.0,
"min": 173.0,
"max": 1343.0,
"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": "1709057920",
"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": "1709058537"
},
"total": 617.088448918,
"count": 1,
"self": 0.585591423999972,
"children": {
"run_training.setup": {
"total": 0.10026265300007253,
"count": 1,
"self": 0.10026265300007253
},
"TrainerController.start_learning": {
"total": 616.402594841,
"count": 1,
"self": 0.8726287869992575,
"children": {
"TrainerController._reset_env": {
"total": 4.600588526000024,
"count": 1,
"self": 4.600588526000024
},
"TrainerController.advance": {
"total": 610.8321861010006,
"count": 18202,
"self": 0.45379428099784036,
"children": {
"env_step": {
"total": 610.3783918200028,
"count": 18202,
"self": 466.430884100003,
"children": {
"SubprocessEnvManager._take_step": {
"total": 143.4977698399964,
"count": 18202,
"self": 2.746298383014391,
"children": {
"TorchPolicy.evaluate": {
"total": 140.75147145698202,
"count": 18202,
"self": 140.75147145698202
}
}
},
"workers": {
"total": 0.44973788000334025,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 614.428081132983,
"count": 18202,
"is_parallel": true,
"self": 287.6885421689856,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007222105999971973,
"count": 1,
"is_parallel": true,
"self": 0.004795874000137701,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002426231999834272,
"count": 10,
"is_parallel": true,
"self": 0.002426231999834272
}
}
},
"UnityEnvironment.step": {
"total": 0.0501907760000222,
"count": 1,
"is_parallel": true,
"self": 0.0009360729998206807,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005430590000514712,
"count": 1,
"is_parallel": true,
"self": 0.0005430590000514712
},
"communicator.exchange": {
"total": 0.04558396800007358,
"count": 1,
"is_parallel": true,
"self": 0.04558396800007358
},
"steps_from_proto": {
"total": 0.0031276760000764625,
"count": 1,
"is_parallel": true,
"self": 0.0006914089998417694,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002436267000234693,
"count": 10,
"is_parallel": true,
"self": 0.002436267000234693
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 326.73953896399746,
"count": 18201,
"is_parallel": true,
"self": 15.83386073701206,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.917645051992736,
"count": 18201,
"is_parallel": true,
"self": 7.917645051992736
},
"communicator.exchange": {
"total": 255.61853390999897,
"count": 18201,
"is_parallel": true,
"self": 255.61853390999897
},
"steps_from_proto": {
"total": 47.36949926499369,
"count": 18201,
"is_parallel": true,
"self": 9.399933729991744,
"children": {
"_process_rank_one_or_two_observation": {
"total": 37.96956553500195,
"count": 182010,
"is_parallel": true,
"self": 37.96956553500195
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0002249990000109392,
"count": 1,
"self": 0.0002249990000109392,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 602.8894313820482,
"count": 849591,
"is_parallel": true,
"self": 20.061611838027034,
"children": {
"process_trajectory": {
"total": 323.75776324902165,
"count": 849591,
"is_parallel": true,
"self": 323.0288117760215,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7289514730001656,
"count": 4,
"is_parallel": true,
"self": 0.7289514730001656
}
}
},
"_update_policy": {
"total": 259.0700562949995,
"count": 90,
"is_parallel": true,
"self": 68.94135359000222,
"children": {
"TorchPPOOptimizer.update": {
"total": 190.1287027049973,
"count": 4587,
"is_parallel": true,
"self": 190.1287027049973
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09696642800008703,
"count": 1,
"self": 0.0013602139999875362,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0956062140000995,
"count": 1,
"self": 0.0956062140000995
}
}
}
}
}
}
}