pryjuli's picture
First Push
26dcefe
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9276163578033447,
"min": 0.9276163578033447,
"max": 2.8632779121398926,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8867.0849609375,
"min": 8867.0849609375,
"max": 29322.828125,
"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": 12.795306205749512,
"min": 0.3656921684741974,
"max": 12.795306205749512,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2495.084716796875,
"min": 70.94428253173828,
"max": 2575.44775390625,
"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": 0.06921824515573498,
"min": 0.06207166787777062,
"max": 0.07461592663643316,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2768729806229399,
"min": 0.24828667151108247,
"max": 0.3589515590508966,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18843339580823393,
"min": 0.11982432146346672,
"max": 0.2916061073979911,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7537335832329357,
"min": 0.4792972858538669,
"max": 1.359570254589997,
"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": 25.454545454545453,
"min": 3.227272727272727,
"max": 25.454545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1120.0,
"min": 142.0,
"max": 1387.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.454545454545453,
"min": 3.227272727272727,
"max": 25.454545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1120.0,
"min": 142.0,
"max": 1387.0,
"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": "1677720741",
"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 /content/ml-agents/config/ppo/SnowballTarget.ymal --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": "1677721226"
},
"total": 484.83977299899993,
"count": 1,
"self": 0.3884839340000781,
"children": {
"run_training.setup": {
"total": 0.12041083400004027,
"count": 1,
"self": 0.12041083400004027
},
"TrainerController.start_learning": {
"total": 484.3308782309998,
"count": 1,
"self": 0.6229694169910545,
"children": {
"TrainerController._reset_env": {
"total": 9.327895680999973,
"count": 1,
"self": 9.327895680999973
},
"TrainerController.advance": {
"total": 474.24535228400896,
"count": 18203,
"self": 0.29923588002679935,
"children": {
"env_step": {
"total": 473.94611640398216,
"count": 18203,
"self": 326.5879869799512,
"children": {
"SubprocessEnvManager._take_step": {
"total": 147.05880693501058,
"count": 18203,
"self": 1.6054827890247907,
"children": {
"TorchPolicy.evaluate": {
"total": 145.4533241459858,
"count": 18203,
"self": 32.0401577849957,
"children": {
"TorchPolicy.sample_actions": {
"total": 113.41316636099009,
"count": 18203,
"self": 113.41316636099009
}
}
}
}
},
"workers": {
"total": 0.2993224890203692,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 482.60048864298824,
"count": 18203,
"is_parallel": true,
"self": 230.66135701596863,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00465056200005165,
"count": 1,
"is_parallel": true,
"self": 0.003205566000133331,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014449959999183193,
"count": 10,
"is_parallel": true,
"self": 0.0014449959999183193
}
}
},
"UnityEnvironment.step": {
"total": 0.04771519700011595,
"count": 1,
"is_parallel": true,
"self": 0.000576123000428197,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00031720399988444115,
"count": 1,
"is_parallel": true,
"self": 0.00031720399988444115
},
"communicator.exchange": {
"total": 0.04483679399982066,
"count": 1,
"is_parallel": true,
"self": 0.04483679399982066
},
"steps_from_proto": {
"total": 0.001985075999982655,
"count": 1,
"is_parallel": true,
"self": 0.00045482399946195073,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015302520005207043,
"count": 10,
"is_parallel": true,
"self": 0.0015302520005207043
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 251.9391316270196,
"count": 18202,
"is_parallel": true,
"self": 9.929406598957712,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.437512647018593,
"count": 18202,
"is_parallel": true,
"self": 5.437512647018593
},
"communicator.exchange": {
"total": 204.04892404001475,
"count": 18202,
"is_parallel": true,
"self": 204.04892404001475
},
"steps_from_proto": {
"total": 32.52328834102855,
"count": 18202,
"is_parallel": true,
"self": 7.3517775719979,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.171510769030647,
"count": 182020,
"is_parallel": true,
"self": 25.171510769030647
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00017907299979924574,
"count": 1,
"self": 0.00017907299979924574,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 470.73686948515774,
"count": 424415,
"is_parallel": true,
"self": 10.784045403041773,
"children": {
"process_trajectory": {
"total": 268.960151190116,
"count": 424415,
"is_parallel": true,
"self": 267.91034185211606,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0498093379999318,
"count": 4,
"is_parallel": true,
"self": 1.0498093379999318
}
}
},
"_update_policy": {
"total": 190.99267289199997,
"count": 90,
"is_parallel": true,
"self": 67.41707417000157,
"children": {
"TorchPPOOptimizer.update": {
"total": 123.5755987219984,
"count": 4587,
"is_parallel": true,
"self": 123.5755987219984
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13448177600002964,
"count": 1,
"self": 0.0008701669999027217,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13361160900012692,
"count": 1,
"self": 0.13361160900012692
}
}
}
}
}
}
}