imflash217's picture
First 200K run of SnowballTarget task
c86f4a2
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9056408405303955,
"min": 0.9056408405303955,
"max": 2.856034755706787,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8647.05859375,
"min": 8647.05859375,
"max": 29217.234375,
"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": 13.025458335876465,
"min": 0.3509628474712372,
"max": 13.025458335876465,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2539.96435546875,
"min": 68.0867919921875,
"max": 2656.65087890625,
"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": 0.06324383921495538,
"min": 0.061881407518882825,
"max": 0.07302005432612338,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25297535685982153,
"min": 0.2475256300755313,
"max": 0.36510027163061687,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17334350468773466,
"min": 0.11824831344168998,
"max": 0.30526266539213703,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6933740187509386,
"min": 0.47299325376675994,
"max": 1.39406437032363,
"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": 25.34090909090909,
"min": 3.3636363636363638,
"max": 25.636363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1115.0,
"min": 148.0,
"max": 1408.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.34090909090909,
"min": 3.3636363636363638,
"max": 25.636363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1115.0,
"min": 148.0,
"max": 1408.0,
"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": "1674795697",
"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=PPO_mlagent_SnowballTarget --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": "1.21.6",
"end_time_seconds": "1674796145"
},
"total": 448.02325903100007,
"count": 1,
"self": 0.39263779299994894,
"children": {
"run_training.setup": {
"total": 0.1064100910000434,
"count": 1,
"self": 0.1064100910000434
},
"TrainerController.start_learning": {
"total": 447.5242111470001,
"count": 1,
"self": 0.6150321840049173,
"children": {
"TrainerController._reset_env": {
"total": 9.771230880999951,
"count": 1,
"self": 9.771230880999951
},
"TrainerController.advance": {
"total": 437.02523953999537,
"count": 18202,
"self": 0.30193229198857807,
"children": {
"env_step": {
"total": 436.7233072480068,
"count": 18202,
"self": 288.2275715080069,
"children": {
"SubprocessEnvManager._take_step": {
"total": 148.19371876000127,
"count": 18202,
"self": 1.5009412889855867,
"children": {
"TorchPolicy.evaluate": {
"total": 146.6927774710157,
"count": 18202,
"self": 34.30216791000066,
"children": {
"TorchPolicy.sample_actions": {
"total": 112.39060956101503,
"count": 18202,
"self": 112.39060956101503
}
}
}
}
},
"workers": {
"total": 0.3020169799985979,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 446.1616458759853,
"count": 18202,
"is_parallel": true,
"self": 211.69096307699624,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0062594019999551165,
"count": 1,
"is_parallel": true,
"self": 0.0037308090001033634,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002528592999851753,
"count": 10,
"is_parallel": true,
"self": 0.002528592999851753
}
}
},
"UnityEnvironment.step": {
"total": 0.033382839999944736,
"count": 1,
"is_parallel": true,
"self": 0.000604186000032314,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023229499993249192,
"count": 1,
"is_parallel": true,
"self": 0.00023229499993249192
},
"communicator.exchange": {
"total": 0.030956253999988803,
"count": 1,
"is_parallel": true,
"self": 0.030956253999988803
},
"steps_from_proto": {
"total": 0.0015901049999911265,
"count": 1,
"is_parallel": true,
"self": 0.0003367909999951735,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001253313999995953,
"count": 10,
"is_parallel": true,
"self": 0.001253313999995953
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 234.47068279898906,
"count": 18201,
"is_parallel": true,
"self": 8.771581882028954,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.100751230986816,
"count": 18201,
"is_parallel": true,
"self": 5.100751230986816
},
"communicator.exchange": {
"total": 189.42582451997987,
"count": 18201,
"is_parallel": true,
"self": 189.42582451997987
},
"steps_from_proto": {
"total": 31.17252516599342,
"count": 18201,
"is_parallel": true,
"self": 6.939562805038008,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.232962360955412,
"count": 182010,
"is_parallel": true,
"self": 24.232962360955412
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.235300002619624e-05,
"count": 1,
"self": 4.235300002619624e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 434.02006828499077,
"count": 371854,
"is_parallel": true,
"self": 9.26180781697633,
"children": {
"process_trajectory": {
"total": 249.9087456790146,
"count": 371854,
"is_parallel": true,
"self": 249.18068105301472,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7280646259998775,
"count": 4,
"is_parallel": true,
"self": 0.7280646259998775
}
}
},
"_update_policy": {
"total": 174.84951478899984,
"count": 90,
"is_parallel": true,
"self": 43.934363737010585,
"children": {
"TorchPPOOptimizer.update": {
"total": 130.91515105198926,
"count": 4584,
"is_parallel": true,
"self": 130.91515105198926
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1126661889998104,
"count": 1,
"self": 0.0008144589996845752,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11185173000012583,
"count": 1,
"self": 0.11185173000012583
}
}
}
}
}
}
}