cyeet's picture
First training
bbf8d27
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8122787475585938,
"min": 0.8122787475585938,
"max": 2.8752448558807373,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7773.5078125,
"min": 7773.5078125,
"max": 29445.3828125,
"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": 12.860902786254883,
"min": 0.3916546106338501,
"max": 12.860902786254883,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2507.8759765625,
"min": 75.98099517822266,
"max": 2611.52197265625,
"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": 0.07049717582412995,
"min": 0.055333400999035234,
"max": 0.0743915538367611,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2819887032965198,
"min": 0.258056099612469,
"max": 0.36472038793783895,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20737430906178905,
"min": 0.12787123386264213,
"max": 0.2687711969310162,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8294972362471562,
"min": 0.5114849354505685,
"max": 1.343855984655081,
"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": 25.5,
"min": 3.1136363636363638,
"max": 25.8,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1122.0,
"min": 137.0,
"max": 1419.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.5,
"min": 3.1136363636363638,
"max": 25.8,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1122.0,
"min": 137.0,
"max": 1419.0,
"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": "1673496138",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "1.21.6",
"end_time_seconds": "1673496557"
},
"total": 419.17856645300003,
"count": 1,
"self": 0.3813477950000106,
"children": {
"run_training.setup": {
"total": 0.10788028299998587,
"count": 1,
"self": 0.10788028299998587
},
"TrainerController.start_learning": {
"total": 418.68933837500003,
"count": 1,
"self": 0.4772141940029542,
"children": {
"TrainerController._reset_env": {
"total": 7.255184633999988,
"count": 1,
"self": 7.255184633999988
},
"TrainerController.advance": {
"total": 410.8400312199972,
"count": 18205,
"self": 0.24612224899749435,
"children": {
"env_step": {
"total": 410.5939089709997,
"count": 18205,
"self": 269.33970539801163,
"children": {
"SubprocessEnvManager._take_step": {
"total": 140.99158717098965,
"count": 18205,
"self": 1.4983287769885578,
"children": {
"TorchPolicy.evaluate": {
"total": 139.4932583940011,
"count": 18205,
"self": 31.798651009989385,
"children": {
"TorchPolicy.sample_actions": {
"total": 107.6946073840117,
"count": 18205,
"self": 107.6946073840117
}
}
}
}
},
"workers": {
"total": 0.2626164019984003,
"count": 18205,
"self": 0.0,
"children": {
"worker_root": {
"total": 417.55248990700557,
"count": 18205,
"is_parallel": true,
"self": 202.14553388100018,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007201651000002585,
"count": 1,
"is_parallel": true,
"self": 0.0045851029999539605,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002616548000048624,
"count": 10,
"is_parallel": true,
"self": 0.002616548000048624
}
}
},
"UnityEnvironment.step": {
"total": 0.03617434300002742,
"count": 1,
"is_parallel": true,
"self": 0.0004990350000753097,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00037532499999315405,
"count": 1,
"is_parallel": true,
"self": 0.00037532499999315405
},
"communicator.exchange": {
"total": 0.033187193999992814,
"count": 1,
"is_parallel": true,
"self": 0.033187193999992814
},
"steps_from_proto": {
"total": 0.002112788999966142,
"count": 1,
"is_parallel": true,
"self": 0.0006826100000125734,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014301789999535686,
"count": 10,
"is_parallel": true,
"self": 0.0014301789999535686
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 215.4069560260054,
"count": 18204,
"is_parallel": true,
"self": 8.238655306997543,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.8585119250111575,
"count": 18204,
"is_parallel": true,
"self": 4.8585119250111575
},
"communicator.exchange": {
"total": 172.98516207800515,
"count": 18204,
"is_parallel": true,
"self": 172.98516207800515
},
"steps_from_proto": {
"total": 29.324626715991542,
"count": 18204,
"is_parallel": true,
"self": 6.201844384993649,
"children": {
"_process_rank_one_or_two_observation": {
"total": 23.122782330997893,
"count": 182040,
"is_parallel": true,
"self": 23.122782330997893
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.1564999946785974e-05,
"count": 1,
"self": 4.1564999946785974e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 408.13379294793634,
"count": 324842,
"is_parallel": true,
"self": 8.189523319986051,
"children": {
"process_trajectory": {
"total": 233.31907884294975,
"count": 324842,
"is_parallel": true,
"self": 232.5725121349497,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7465667080000458,
"count": 4,
"is_parallel": true,
"self": 0.7465667080000458
}
}
},
"_update_policy": {
"total": 166.62519078500054,
"count": 90,
"is_parallel": true,
"self": 44.63059812599653,
"children": {
"TorchPPOOptimizer.update": {
"total": 121.99459265900401,
"count": 4587,
"is_parallel": true,
"self": 121.99459265900401
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11686676199997237,
"count": 1,
"self": 0.0008845699999255885,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11598219200004678,
"count": 1,
"self": 0.11598219200004678
}
}
}
}
}
}
}