Schwarzschild009's picture
first unity agent
a179a86
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.984889030456543,
"min": 0.984889030456543,
"max": 2.862149953842163,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9392.88671875,
"min": 9392.88671875,
"max": 29374.24609375,
"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": 12.82288646697998,
"min": 0.5382060408592224,
"max": 12.82288646697998,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2500.462890625,
"min": 104.41197204589844,
"max": 2608.9033203125,
"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": 0.07133691690322332,
"min": 0.06289976251530735,
"max": 0.07312194977067503,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28534766761289326,
"min": 0.2598244760203456,
"max": 0.35285309080363203,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22140959993589157,
"min": 0.13377038576964326,
"max": 0.2616093073405471,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8856383997435663,
"min": 0.535081543078573,
"max": 1.3080465367027356,
"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": 24.75,
"min": 3.8636363636363638,
"max": 25.672727272727272,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1089.0,
"min": 170.0,
"max": 1412.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.75,
"min": 3.8636363636363638,
"max": 25.672727272727272,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1089.0,
"min": 170.0,
"max": 1412.0,
"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": "1678907394",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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=SnowballTarget1 --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1678907858"
},
"total": 463.99017710399994,
"count": 1,
"self": 0.43829005899993945,
"children": {
"run_training.setup": {
"total": 0.10418097100000523,
"count": 1,
"self": 0.10418097100000523
},
"TrainerController.start_learning": {
"total": 463.447706074,
"count": 1,
"self": 0.578169236995052,
"children": {
"TrainerController._reset_env": {
"total": 10.64142123800002,
"count": 1,
"self": 10.64142123800002
},
"TrainerController.advance": {
"total": 452.09883183400495,
"count": 18200,
"self": 0.3009180260004314,
"children": {
"env_step": {
"total": 451.7979138080045,
"count": 18200,
"self": 324.8723588909959,
"children": {
"SubprocessEnvManager._take_step": {
"total": 126.65242671500289,
"count": 18200,
"self": 2.612887883997928,
"children": {
"TorchPolicy.evaluate": {
"total": 124.03953883100496,
"count": 18200,
"self": 124.03953883100496
}
}
},
"workers": {
"total": 0.2731282020057506,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 461.88627198199663,
"count": 18200,
"is_parallel": true,
"self": 220.37828096399375,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006838281999989704,
"count": 1,
"is_parallel": true,
"self": 0.00515342499994631,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016848570000433938,
"count": 10,
"is_parallel": true,
"self": 0.0016848570000433938
}
}
},
"UnityEnvironment.step": {
"total": 0.03416258300001118,
"count": 1,
"is_parallel": true,
"self": 0.0005305090000433665,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002561659999855692,
"count": 1,
"is_parallel": true,
"self": 0.0002561659999855692
},
"communicator.exchange": {
"total": 0.03155104899997241,
"count": 1,
"is_parallel": true,
"self": 0.03155104899997241
},
"steps_from_proto": {
"total": 0.0018248590000098375,
"count": 1,
"is_parallel": true,
"self": 0.0004019249999487329,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014229340000611046,
"count": 10,
"is_parallel": true,
"self": 0.0014229340000611046
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 241.50799101800288,
"count": 18199,
"is_parallel": true,
"self": 9.577960848996895,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.193308211997419,
"count": 18199,
"is_parallel": true,
"self": 5.193308211997419
},
"communicator.exchange": {
"total": 196.00579415800536,
"count": 18199,
"is_parallel": true,
"self": 196.00579415800536
},
"steps_from_proto": {
"total": 30.73092779900321,
"count": 18199,
"is_parallel": true,
"self": 6.085870619990146,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.645057179013065,
"count": 181990,
"is_parallel": true,
"self": 24.645057179013065
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 3.297500006738119e-05,
"count": 1,
"self": 3.297500006738119e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 448.7299783160135,
"count": 412062,
"is_parallel": true,
"self": 9.885440473028325,
"children": {
"process_trajectory": {
"total": 252.07417236998504,
"count": 412062,
"is_parallel": true,
"self": 250.92205995398513,
"children": {
"RLTrainer._checkpoint": {
"total": 1.152112415999909,
"count": 4,
"is_parallel": true,
"self": 1.152112415999909
}
}
},
"_update_policy": {
"total": 186.77036547300014,
"count": 90,
"is_parallel": true,
"self": 67.72660280099637,
"children": {
"TorchPPOOptimizer.update": {
"total": 119.04376267200377,
"count": 4587,
"is_parallel": true,
"self": 119.04376267200377
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12925078999990092,
"count": 1,
"self": 0.0008936739999398924,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12835711599996102,
"count": 1,
"self": 0.12835711599996102
}
}
}
}
}
}
}