TheSuperGroot's picture
First Push
cfc5c6d verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9472379684448242,
"min": 0.9398645758628845,
"max": 2.8735647201538086,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9054.6474609375,
"min": 9054.6474609375,
"max": 29459.78515625,
"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": 12.657986640930176,
"min": 0.1709822416305542,
"max": 12.731136322021484,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2468.307373046875,
"min": 33.170555114746094,
"max": 2597.15185546875,
"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": 0.07188583496092321,
"min": 0.06340149212223432,
"max": 0.0744872206126399,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28754333984369285,
"min": 0.2536059684889373,
"max": 0.3686273755366154,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.216255473447781,
"min": 0.10174676027222007,
"max": 0.2785939880299802,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.865021893791124,
"min": 0.4069870410888803,
"max": 1.3920926168268803,
"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": 24.454545454545453,
"min": 2.659090909090909,
"max": 25.09090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1076.0,
"min": 117.0,
"max": 1356.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.454545454545453,
"min": 2.659090909090909,
"max": 25.09090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1076.0,
"min": 117.0,
"max": 1356.0,
"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": "1712065527",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1712066164"
},
"total": 637.3078053669999,
"count": 1,
"self": 0.6024234650000153,
"children": {
"run_training.setup": {
"total": 0.08455102300001727,
"count": 1,
"self": 0.08455102300001727
},
"TrainerController.start_learning": {
"total": 636.6208308789999,
"count": 1,
"self": 0.9163425270014613,
"children": {
"TrainerController._reset_env": {
"total": 3.7834300490000032,
"count": 1,
"self": 3.7834300490000032
},
"TrainerController.advance": {
"total": 631.8100937319983,
"count": 18202,
"self": 0.4499380680115337,
"children": {
"env_step": {
"total": 631.3601556639868,
"count": 18202,
"self": 483.08567821296447,
"children": {
"SubprocessEnvManager._take_step": {
"total": 147.8132074420165,
"count": 18202,
"self": 2.569772364034179,
"children": {
"TorchPolicy.evaluate": {
"total": 145.24343507798233,
"count": 18202,
"self": 145.24343507798233
}
}
},
"workers": {
"total": 0.4612700090058297,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 634.4666289030104,
"count": 18202,
"is_parallel": true,
"self": 294.01818183199543,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008201155999927323,
"count": 1,
"is_parallel": true,
"self": 0.005508635000069262,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0026925209998580613,
"count": 10,
"is_parallel": true,
"self": 0.0026925209998580613
}
}
},
"UnityEnvironment.step": {
"total": 0.04879633100006231,
"count": 1,
"is_parallel": true,
"self": 0.0009693570001445551,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005298399998991954,
"count": 1,
"is_parallel": true,
"self": 0.0005298399998991954
},
"communicator.exchange": {
"total": 0.044739605000017946,
"count": 1,
"is_parallel": true,
"self": 0.044739605000017946
},
"steps_from_proto": {
"total": 0.0025575290000006135,
"count": 1,
"is_parallel": true,
"self": 0.0004887120002194933,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00206881699978112,
"count": 10,
"is_parallel": true,
"self": 0.00206881699978112
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 340.4484470710149,
"count": 18201,
"is_parallel": true,
"self": 16.500011152040543,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.240113364993931,
"count": 18201,
"is_parallel": true,
"self": 8.240113364993931
},
"communicator.exchange": {
"total": 267.38742231598553,
"count": 18201,
"is_parallel": true,
"self": 267.38742231598553
},
"steps_from_proto": {
"total": 48.32090023799492,
"count": 18201,
"is_parallel": true,
"self": 9.771228209994433,
"children": {
"_process_rank_one_or_two_observation": {
"total": 38.54967202800049,
"count": 182010,
"is_parallel": true,
"self": 38.54967202800049
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0003738670000075217,
"count": 1,
"self": 0.0003738670000075217,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 624.0620433709915,
"count": 867357,
"is_parallel": true,
"self": 20.102273329060154,
"children": {
"process_trajectory": {
"total": 344.67869158193025,
"count": 867357,
"is_parallel": true,
"self": 343.7217732339302,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9569183480000447,
"count": 4,
"is_parallel": true,
"self": 0.9569183480000447
}
}
},
"_update_policy": {
"total": 259.28107846000114,
"count": 90,
"is_parallel": true,
"self": 66.19311832400831,
"children": {
"TorchPPOOptimizer.update": {
"total": 193.08796013599283,
"count": 4587,
"is_parallel": true,
"self": 193.08796013599283
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11059070400006021,
"count": 1,
"self": 0.001659268000139491,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10893143599992072,
"count": 1,
"self": 0.10893143599992072
}
}
}
}
}
}
}