Taratata's picture
V1
f48bb4c
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0078576803207397,
"min": 0.9887528419494629,
"max": 2.86478853225708,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9623.025390625,
"min": 9623.025390625,
"max": 29527.375,
"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": 12.021263122558594,
"min": 0.328925758600235,
"max": 12.021263122558594,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2344.146240234375,
"min": 63.81159973144531,
"max": 2420.455078125,
"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": 0.06587109452997467,
"min": 0.06047929655776041,
"max": 0.07254534116238538,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26348437811989867,
"min": 0.24191718623104164,
"max": 0.3562002987579463,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17323438896268023,
"min": 0.11478611321859608,
"max": 0.26805297131924066,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6929375558507209,
"min": 0.4591444528743843,
"max": 1.2721038279580135,
"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": 23.431818181818183,
"min": 3.3863636363636362,
"max": 23.854545454545455,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1031.0,
"min": 149.0,
"max": 1312.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.431818181818183,
"min": 3.3863636363636362,
"max": 23.854545454545455,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1031.0,
"min": 149.0,
"max": 1312.0,
"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": "1677610696",
"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=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": "1677611184"
},
"total": 488.254712381,
"count": 1,
"self": 0.4401181310000766,
"children": {
"run_training.setup": {
"total": 0.11258192099990083,
"count": 1,
"self": 0.11258192099990083
},
"TrainerController.start_learning": {
"total": 487.702012329,
"count": 1,
"self": 0.6356440390080706,
"children": {
"TrainerController._reset_env": {
"total": 9.02245871599996,
"count": 1,
"self": 9.02245871599996
},
"TrainerController.advance": {
"total": 477.91851435099204,
"count": 18203,
"self": 0.3004453699934402,
"children": {
"env_step": {
"total": 477.6180689809986,
"count": 18203,
"self": 328.37736298798814,
"children": {
"SubprocessEnvManager._take_step": {
"total": 148.91560819699782,
"count": 18203,
"self": 1.6207345579954335,
"children": {
"TorchPolicy.evaluate": {
"total": 147.2948736390024,
"count": 18203,
"self": 33.58507463500234,
"children": {
"TorchPolicy.sample_actions": {
"total": 113.70979900400005,
"count": 18203,
"self": 113.70979900400005
}
}
}
}
},
"workers": {
"total": 0.325097796012642,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 486.0679814310047,
"count": 18203,
"is_parallel": true,
"self": 236.2687460490015,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007203123999943273,
"count": 1,
"is_parallel": true,
"self": 0.003481496000063089,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0037216279998801838,
"count": 10,
"is_parallel": true,
"self": 0.0037216279998801838
}
}
},
"UnityEnvironment.step": {
"total": 0.05427311500000087,
"count": 1,
"is_parallel": true,
"self": 0.0005773190000581963,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004226830000106929,
"count": 1,
"is_parallel": true,
"self": 0.0004226830000106929
},
"communicator.exchange": {
"total": 0.0515085069999941,
"count": 1,
"is_parallel": true,
"self": 0.0515085069999941
},
"steps_from_proto": {
"total": 0.001764605999937885,
"count": 1,
"is_parallel": true,
"self": 0.0004189759999917442,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013456299999461407,
"count": 10,
"is_parallel": true,
"self": 0.0013456299999461407
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 249.7992353820032,
"count": 18202,
"is_parallel": true,
"self": 9.760481640003832,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.527964058999373,
"count": 18202,
"is_parallel": true,
"self": 5.527964058999373
},
"communicator.exchange": {
"total": 200.64416831799952,
"count": 18202,
"is_parallel": true,
"self": 200.64416831799952
},
"steps_from_proto": {
"total": 33.86662136500047,
"count": 18202,
"is_parallel": true,
"self": 7.779188279050572,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.087433085949897,
"count": 182020,
"is_parallel": true,
"self": 26.087433085949897
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001263289999542394,
"count": 1,
"self": 0.0001263289999542394,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 474.2824700890337,
"count": 424022,
"is_parallel": true,
"self": 11.219965981996552,
"children": {
"process_trajectory": {
"total": 270.889219137037,
"count": 424022,
"is_parallel": true,
"self": 270.08625773603694,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8029614010000614,
"count": 4,
"is_parallel": true,
"self": 0.8029614010000614
}
}
},
"_update_policy": {
"total": 192.17328497000017,
"count": 90,
"is_parallel": true,
"self": 66.85611099100618,
"children": {
"TorchPPOOptimizer.update": {
"total": 125.31717397899399,
"count": 4587,
"is_parallel": true,
"self": 125.31717397899399
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12526889399998709,
"count": 1,
"self": 0.0009169840000140539,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12435190999997303,
"count": 1,
"self": 0.12435190999997303
}
}
}
}
}
}
}