tizayi's picture
First Push
a3dba94 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8832919597625732,
"min": 0.8832919597625732,
"max": 2.8543243408203125,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8433.671875,
"min": 8433.671875,
"max": 29231.13671875,
"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": 12.736458778381348,
"min": 0.3304445743560791,
"max": 12.736458778381348,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2483.609375,
"min": 64.10624694824219,
"max": 2593.02197265625,
"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": 0.07288557454768463,
"min": 0.06364095257866247,
"max": 0.07442322756556392,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2915422981907385,
"min": 0.25456381031464986,
"max": 0.3721161378278196,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1895520837941006,
"min": 0.11043294009469522,
"max": 0.27730751283028543,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7582083351764024,
"min": 0.44173176037878087,
"max": 1.3865375641514273,
"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": 24.954545454545453,
"min": 3.1136363636363638,
"max": 25.272727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1098.0,
"min": 137.0,
"max": 1390.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.954545454545453,
"min": 3.1136363636363638,
"max": 25.272727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1098.0,
"min": 137.0,
"max": 1390.0,
"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": "1707319229",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn 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": "2.2.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1707319654"
},
"total": 425.14800809400003,
"count": 1,
"self": 0.4392334450000135,
"children": {
"run_training.setup": {
"total": 0.051017150999996375,
"count": 1,
"self": 0.051017150999996375
},
"TrainerController.start_learning": {
"total": 424.657757498,
"count": 1,
"self": 0.5303788029968928,
"children": {
"TrainerController._reset_env": {
"total": 3.1524567230000002,
"count": 1,
"self": 3.1524567230000002
},
"TrainerController.advance": {
"total": 420.8875908720031,
"count": 18199,
"self": 0.2510336580071453,
"children": {
"env_step": {
"total": 420.63655721399596,
"count": 18199,
"self": 271.1741867769799,
"children": {
"SubprocessEnvManager._take_step": {
"total": 149.19280035701058,
"count": 18199,
"self": 1.3837687820097244,
"children": {
"TorchPolicy.evaluate": {
"total": 147.80903157500086,
"count": 18199,
"self": 147.80903157500086
}
}
},
"workers": {
"total": 0.269570080005451,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 423.612734598002,
"count": 18199,
"is_parallel": true,
"self": 209.37580519100948,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005032769999957054,
"count": 1,
"is_parallel": true,
"self": 0.0036065470001176436,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014262229998394105,
"count": 10,
"is_parallel": true,
"self": 0.0014262229998394105
}
}
},
"UnityEnvironment.step": {
"total": 0.03761827499999981,
"count": 1,
"is_parallel": true,
"self": 0.0006158909999385287,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00043247099995369354,
"count": 1,
"is_parallel": true,
"self": 0.00043247099995369354
},
"communicator.exchange": {
"total": 0.03468365100002302,
"count": 1,
"is_parallel": true,
"self": 0.03468365100002302
},
"steps_from_proto": {
"total": 0.001886262000084571,
"count": 1,
"is_parallel": true,
"self": 0.0003992240002617109,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00148703799982286,
"count": 10,
"is_parallel": true,
"self": 0.00148703799982286
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 214.23692940699254,
"count": 18198,
"is_parallel": true,
"self": 10.260970109966593,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.311893807998445,
"count": 18198,
"is_parallel": true,
"self": 5.311893807998445
},
"communicator.exchange": {
"total": 165.99698821102254,
"count": 18198,
"is_parallel": true,
"self": 165.99698821102254
},
"steps_from_proto": {
"total": 32.66707727800497,
"count": 18198,
"is_parallel": true,
"self": 6.002216754019969,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.664860523985,
"count": 181980,
"is_parallel": true,
"self": 26.664860523985
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001224259999617061,
"count": 1,
"self": 0.0001224259999617061,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 415.540296978077,
"count": 650437,
"is_parallel": true,
"self": 13.546077614105911,
"children": {
"process_trajectory": {
"total": 228.82654840597127,
"count": 650437,
"is_parallel": true,
"self": 228.08116569997162,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7453827059996456,
"count": 4,
"is_parallel": true,
"self": 0.7453827059996456
}
}
},
"_update_policy": {
"total": 173.1676709579998,
"count": 90,
"is_parallel": true,
"self": 48.17094734100283,
"children": {
"TorchPPOOptimizer.update": {
"total": 124.99672361699697,
"count": 4584,
"is_parallel": true,
"self": 124.99672361699697
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08720867400006682,
"count": 1,
"self": 0.0009409029999005725,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08626777100016625,
"count": 1,
"self": 0.08626777100016625
}
}
}
}
}
}
}