JonhL's picture
First Push
cf0b322
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9209079742431641,
"min": 0.9209079742431641,
"max": 2.8554835319519043,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8843.4794921875,
"min": 8843.4794921875,
"max": 29274.416015625,
"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": 13.449316024780273,
"min": 0.2423088401556015,
"max": 13.450636863708496,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2622.61669921875,
"min": 47.00791549682617,
"max": 2743.929931640625,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0523188324085216,
"min": 0.04013436694003758,
"max": 0.05276291729921164,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2092753296340864,
"min": 0.16053746776015032,
"max": 0.2638145864960582,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22301143826916814,
"min": 0.1176882938016206,
"max": 0.30404930288592974,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8920457530766726,
"min": 0.4707531752064824,
"max": 1.5202465144296486,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 2.694009730600002e-05,
"min": 2.694009730600002e-05,
"max": 0.000972940002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.00010776038922400007,
"min": 0.00010776038922400007,
"max": 0.004617200038280001,
"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": 0.9617200000000001,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00014443060000000012,
"min": 0.00014443060000000012,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000005,
"min": 0.0005777224000000005,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.84090909090909,
"min": 3.590909090909091,
"max": 26.727272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1137.0,
"min": 158.0,
"max": 1470.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.84090909090909,
"min": 3.590909090909091,
"max": 26.727272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1137.0,
"min": 158.0,
"max": 1470.0,
"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": "1697673905",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.0.1+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1697674443"
},
"total": 537.8326256340001,
"count": 1,
"self": 1.095050332000028,
"children": {
"run_training.setup": {
"total": 0.0577325720000772,
"count": 1,
"self": 0.0577325720000772
},
"TrainerController.start_learning": {
"total": 536.67984273,
"count": 1,
"self": 0.7898188320272084,
"children": {
"TrainerController._reset_env": {
"total": 0.9289747669999997,
"count": 1,
"self": 0.9289747669999997
},
"TrainerController.advance": {
"total": 534.8079829349728,
"count": 18212,
"self": 0.41277372999491035,
"children": {
"env_step": {
"total": 534.3952092049778,
"count": 18212,
"self": 406.42033750798305,
"children": {
"SubprocessEnvManager._take_step": {
"total": 127.5648535529881,
"count": 18212,
"self": 2.1792076299880137,
"children": {
"TorchPolicy.evaluate": {
"total": 125.38564592300008,
"count": 18212,
"self": 125.38564592300008
}
}
},
"workers": {
"total": 0.410018144006699,
"count": 18212,
"self": 0.0,
"children": {
"worker_root": {
"total": 534.6935707599924,
"count": 18212,
"is_parallel": true,
"self": 223.55565343199066,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0053576260000909315,
"count": 1,
"is_parallel": true,
"self": 0.00380563200008055,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015519940000103816,
"count": 10,
"is_parallel": true,
"self": 0.0015519940000103816
}
}
},
"UnityEnvironment.step": {
"total": 0.05327498899998773,
"count": 1,
"is_parallel": true,
"self": 0.000769654000009723,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039501599997038284,
"count": 1,
"is_parallel": true,
"self": 0.00039501599997038284
},
"communicator.exchange": {
"total": 0.04984746200000245,
"count": 1,
"is_parallel": true,
"self": 0.04984746200000245
},
"steps_from_proto": {
"total": 0.0022628570000051695,
"count": 1,
"is_parallel": true,
"self": 0.0004558429997132407,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018070140002919288,
"count": 10,
"is_parallel": true,
"self": 0.0018070140002919288
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 311.1379173280018,
"count": 18211,
"is_parallel": true,
"self": 14.202302401010684,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.6041742179920675,
"count": 18211,
"is_parallel": true,
"self": 7.6041742179920675
},
"communicator.exchange": {
"total": 245.45814734599116,
"count": 18211,
"is_parallel": true,
"self": 245.45814734599116
},
"steps_from_proto": {
"total": 43.87329336300786,
"count": 18211,
"is_parallel": true,
"self": 8.699654178067362,
"children": {
"_process_rank_one_or_two_observation": {
"total": 35.1736391849405,
"count": 182110,
"is_parallel": true,
"self": 35.1736391849405
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015720800001872703,
"count": 1,
"self": 0.00015720800001872703,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 529.8500154590724,
"count": 593133,
"is_parallel": true,
"self": 13.522208833063473,
"children": {
"process_trajectory": {
"total": 309.82204094700865,
"count": 593133,
"is_parallel": true,
"self": 308.55683323500864,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2652077120000058,
"count": 4,
"is_parallel": true,
"self": 1.2652077120000058
}
}
},
"_update_policy": {
"total": 206.50576567900032,
"count": 90,
"is_parallel": true,
"self": 72.37556248900216,
"children": {
"TorchPPOOptimizer.update": {
"total": 134.13020318999816,
"count": 2160,
"is_parallel": true,
"self": 134.13020318999816
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1529089880000356,
"count": 1,
"self": 0.001432823000186545,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15147616499984906,
"count": 1,
"self": 0.15147616499984906
}
}
}
}
}
}
}