abarekatain's picture
Initial Commit
29fad78
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9128385186195374,
"min": 0.9006667733192444,
"max": 2.874990463256836,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8705.7412109375,
"min": 8705.7412109375,
"max": 29442.77734375,
"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": 12.861756324768066,
"min": 0.35971081256866455,
"max": 12.861756324768066,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2508.04248046875,
"min": 69.78389739990234,
"max": 2623.65673828125,
"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": 0.07109628585292775,
"min": 0.06314074566477097,
"max": 0.07364906079901096,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.284385143411711,
"min": 0.2525629826590839,
"max": 0.3616243029139107,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21292749281023063,
"min": 0.13703707935215503,
"max": 0.2705642942120047,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8517099712409225,
"min": 0.5481483174086201,
"max": 1.3528214710600235,
"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": 25.318181818181817,
"min": 3.6818181818181817,
"max": 25.472727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1114.0,
"min": 162.0,
"max": 1401.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.318181818181817,
"min": 3.6818181818181817,
"max": 25.472727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1114.0,
"min": 162.0,
"max": 1401.0,
"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": "1677673729",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.22.4",
"end_time_seconds": "1677674189"
},
"total": 459.61847149799996,
"count": 1,
"self": 0.388265027999978,
"children": {
"run_training.setup": {
"total": 0.10795577699991554,
"count": 1,
"self": 0.10795577699991554
},
"TrainerController.start_learning": {
"total": 459.12225069300007,
"count": 1,
"self": 0.5227925539741136,
"children": {
"TrainerController._reset_env": {
"total": 9.366231575000029,
"count": 1,
"self": 9.366231575000029
},
"TrainerController.advance": {
"total": 449.11475197202594,
"count": 18200,
"self": 0.26070388905304753,
"children": {
"env_step": {
"total": 448.8540480829729,
"count": 18200,
"self": 308.2974221359382,
"children": {
"SubprocessEnvManager._take_step": {
"total": 140.28014167100696,
"count": 18200,
"self": 1.4926424940128982,
"children": {
"TorchPolicy.evaluate": {
"total": 138.78749917699406,
"count": 18200,
"self": 31.861453510997308,
"children": {
"TorchPolicy.sample_actions": {
"total": 106.92604566599675,
"count": 18200,
"self": 106.92604566599675
}
}
}
}
},
"workers": {
"total": 0.2764842760277588,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 457.6728036590225,
"count": 18200,
"is_parallel": true,
"self": 223.8481277039773,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0062565999999151245,
"count": 1,
"is_parallel": true,
"self": 0.00448412300011114,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017724769998039847,
"count": 10,
"is_parallel": true,
"self": 0.0017724769998039847
}
}
},
"UnityEnvironment.step": {
"total": 0.04450737900015156,
"count": 1,
"is_parallel": true,
"self": 0.0005474300000969379,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003381960000297113,
"count": 1,
"is_parallel": true,
"self": 0.0003381960000297113
},
"communicator.exchange": {
"total": 0.04184465100001944,
"count": 1,
"is_parallel": true,
"self": 0.04184465100001944
},
"steps_from_proto": {
"total": 0.0017771020000054705,
"count": 1,
"is_parallel": true,
"self": 0.0004221179997330182,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013549840002724522,
"count": 10,
"is_parallel": true,
"self": 0.0013549840002724522
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 233.82467595504522,
"count": 18199,
"is_parallel": true,
"self": 9.530548149052265,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.290373066976144,
"count": 18199,
"is_parallel": true,
"self": 5.290373066976144
},
"communicator.exchange": {
"total": 187.87056233100043,
"count": 18199,
"is_parallel": true,
"self": 187.87056233100043
},
"steps_from_proto": {
"total": 31.133192408016384,
"count": 18199,
"is_parallel": true,
"self": 6.755320794015006,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.37787161400138,
"count": 181990,
"is_parallel": true,
"self": 24.37787161400138
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.127200008952059e-05,
"count": 1,
"self": 4.127200008952059e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 445.78324271016186,
"count": 397008,
"is_parallel": true,
"self": 9.788816593278852,
"children": {
"process_trajectory": {
"total": 255.31590574388588,
"count": 397008,
"is_parallel": true,
"self": 254.50793347288595,
"children": {
"RLTrainer._checkpoint": {
"total": 0.807972270999926,
"count": 4,
"is_parallel": true,
"self": 0.807972270999926
}
}
},
"_update_policy": {
"total": 180.67852037299713,
"count": 90,
"is_parallel": true,
"self": 63.56365897398837,
"children": {
"TorchPPOOptimizer.update": {
"total": 117.11486139900876,
"count": 4587,
"is_parallel": true,
"self": 117.11486139900876
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11843331999989459,
"count": 1,
"self": 0.0008698139999978594,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11756350599989673,
"count": 1,
"self": 0.11756350599989673
}
}
}
}
}
}
}