samzoozi's picture
First Push
1ecdcf1
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9239097237586975,
"min": 0.8937488198280334,
"max": 2.866297960281372,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8821.490234375,
"min": 8663.548828125,
"max": 29385.287109375,
"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": 11.462961196899414,
"min": 0.42796435952186584,
"max": 11.462961196899414,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2235.27734375,
"min": 83.02508544921875,
"max": 2325.22216796875,
"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": 0.06313179454039475,
"min": 0.06042563514647019,
"max": 0.07391154463238862,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.252527178161579,
"min": 0.252527178161579,
"max": 0.3521762907815476,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1804715279197576,
"min": 0.09767482748401224,
"max": 0.2899374908091975,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7218861116790304,
"min": 0.39069930993604896,
"max": 1.4496874540459876,
"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": 22.568181818181817,
"min": 2.7954545454545454,
"max": 22.727272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 993.0,
"min": 123.0,
"max": 1250.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 22.568181818181817,
"min": 2.7954545454545454,
"max": 22.727272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 993.0,
"min": 123.0,
"max": 1250.0,
"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": "1699161022",
"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": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1699161484"
},
"total": 462.52969144200006,
"count": 1,
"self": 0.44746449000001576,
"children": {
"run_training.setup": {
"total": 0.042943564999973205,
"count": 1,
"self": 0.042943564999973205
},
"TrainerController.start_learning": {
"total": 462.03928338700007,
"count": 1,
"self": 0.5169621520022929,
"children": {
"TrainerController._reset_env": {
"total": 8.792273209999962,
"count": 1,
"self": 8.792273209999962
},
"TrainerController.advance": {
"total": 452.6471637649977,
"count": 18199,
"self": 0.2511739609815322,
"children": {
"env_step": {
"total": 452.39598980401615,
"count": 18199,
"self": 307.7647335650156,
"children": {
"SubprocessEnvManager._take_step": {
"total": 144.36708332200476,
"count": 18199,
"self": 1.3984841620086854,
"children": {
"TorchPolicy.evaluate": {
"total": 142.96859915999607,
"count": 18199,
"self": 142.96859915999607
}
}
},
"workers": {
"total": 0.2641729169957898,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 460.85153733500306,
"count": 18199,
"is_parallel": true,
"self": 227.36206070998912,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0051402899999857254,
"count": 1,
"is_parallel": true,
"self": 0.0036543449998589494,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001485945000126776,
"count": 10,
"is_parallel": true,
"self": 0.001485945000126776
}
}
},
"UnityEnvironment.step": {
"total": 0.03356321400008255,
"count": 1,
"is_parallel": true,
"self": 0.0007067680002137422,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003884609999431632,
"count": 1,
"is_parallel": true,
"self": 0.0003884609999431632
},
"communicator.exchange": {
"total": 0.03061803199989299,
"count": 1,
"is_parallel": true,
"self": 0.03061803199989299
},
"steps_from_proto": {
"total": 0.0018499530000326558,
"count": 1,
"is_parallel": true,
"self": 0.0003700790001630594,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014798739998695964,
"count": 10,
"is_parallel": true,
"self": 0.0014798739998695964
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 233.48947662501394,
"count": 18198,
"is_parallel": true,
"self": 10.461227823040645,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.222511194986396,
"count": 18198,
"is_parallel": true,
"self": 5.222511194986396
},
"communicator.exchange": {
"total": 184.83462250099979,
"count": 18198,
"is_parallel": true,
"self": 184.83462250099979
},
"steps_from_proto": {
"total": 32.97111510598711,
"count": 18198,
"is_parallel": true,
"self": 6.079200426933085,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.891914679054025,
"count": 181980,
"is_parallel": true,
"self": 26.891914679054025
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00016941500007305876,
"count": 1,
"self": 0.00016941500007305876,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 448.9281537749837,
"count": 462147,
"is_parallel": true,
"self": 9.784974608070684,
"children": {
"process_trajectory": {
"total": 252.50088284491187,
"count": 462147,
"is_parallel": true,
"self": 251.6172449029117,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8836379420001776,
"count": 4,
"is_parallel": true,
"self": 0.8836379420001776
}
}
},
"_update_policy": {
"total": 186.64229632200113,
"count": 90,
"is_parallel": true,
"self": 56.52549566099367,
"children": {
"TorchPPOOptimizer.update": {
"total": 130.11680066100746,
"count": 4584,
"is_parallel": true,
"self": 130.11680066100746
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08271484500005499,
"count": 1,
"self": 0.0011938890002056723,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08152095599984932,
"count": 1,
"self": 0.08152095599984932
}
}
}
}
}
}
}