qwerder's picture
First Push
fc6870a verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7579612731933594,
"min": 0.7579612731933594,
"max": 2.862020254135132,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7203.6640625,
"min": 7203.6640625,
"max": 29215.50390625,
"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": 13.378022193908691,
"min": 0.388624906539917,
"max": 13.378022193908691,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2608.71435546875,
"min": 75.39323425292969,
"max": 2714.44775390625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0729475585006488,
"min": 0.06005878311942284,
"max": 0.0729475585006488,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2917902340025952,
"min": 0.24023513247769135,
"max": 0.3625560416109567,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1807383291934635,
"min": 0.13754928217146217,
"max": 0.29719077291734075,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.722953316773854,
"min": 0.5501971286858487,
"max": 1.293348251020207,
"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.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.Environment.CumulativeReward.mean": {
"value": 26.886363636363637,
"min": 3.9545454545454546,
"max": 26.886363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1183.0,
"min": 174.0,
"max": 1432.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.886363636363637,
"min": 3.9545454545454546,
"max": 26.886363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1183.0,
"min": 174.0,
"max": 1432.0,
"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": "1764101617",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1764102044"
},
"total": 427.68389748899995,
"count": 1,
"self": 0.43770558899996104,
"children": {
"run_training.setup": {
"total": 0.026112506000004032,
"count": 1,
"self": 0.026112506000004032
},
"TrainerController.start_learning": {
"total": 427.220079394,
"count": 1,
"self": 0.3242211639887955,
"children": {
"TrainerController._reset_env": {
"total": 3.0016701360000297,
"count": 1,
"self": 3.0016701360000297
},
"TrainerController.advance": {
"total": 423.81792256601113,
"count": 18192,
"self": 0.3525386340214709,
"children": {
"env_step": {
"total": 307.52753240799007,
"count": 18192,
"self": 240.53095896500145,
"children": {
"SubprocessEnvManager._take_step": {
"total": 66.79261074699787,
"count": 18192,
"self": 1.1966683589843115,
"children": {
"TorchPolicy.evaluate": {
"total": 65.59594238801355,
"count": 18192,
"self": 65.59594238801355
}
}
},
"workers": {
"total": 0.20396269599075367,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 425.2741125009985,
"count": 18192,
"is_parallel": true,
"self": 213.788427516997,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004486698000050637,
"count": 1,
"is_parallel": true,
"self": 0.002997658000026604,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014890400000240334,
"count": 10,
"is_parallel": true,
"self": 0.0014890400000240334
}
}
},
"UnityEnvironment.step": {
"total": 0.06809767099991859,
"count": 1,
"is_parallel": true,
"self": 0.0005806039997651169,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004090710000355102,
"count": 1,
"is_parallel": true,
"self": 0.0004090710000355102
},
"communicator.exchange": {
"total": 0.06337222700005896,
"count": 1,
"is_parallel": true,
"self": 0.06337222700005896
},
"steps_from_proto": {
"total": 0.0037357690000590082,
"count": 1,
"is_parallel": true,
"self": 0.0003194019999455122,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003416367000113496,
"count": 10,
"is_parallel": true,
"self": 0.003416367000113496
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 211.48568498400152,
"count": 18191,
"is_parallel": true,
"self": 10.020967721973989,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.199471307018825,
"count": 18191,
"is_parallel": true,
"self": 5.199471307018825
},
"communicator.exchange": {
"total": 161.21578588901434,
"count": 18191,
"is_parallel": true,
"self": 161.21578588901434
},
"steps_from_proto": {
"total": 35.04946006599437,
"count": 18191,
"is_parallel": true,
"self": 6.392122803007396,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.65733726298697,
"count": 181910,
"is_parallel": true,
"self": 28.65733726298697
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 115.9378515239996,
"count": 18192,
"self": 0.4077320119979504,
"children": {
"process_trajectory": {
"total": 25.828904373002388,
"count": 18192,
"self": 25.324340079002354,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5045642940000334,
"count": 4,
"self": 0.5045642940000334
}
}
},
"_update_policy": {
"total": 89.70121513899926,
"count": 90,
"self": 36.535731585994654,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.165483553004606,
"count": 4587,
"self": 53.165483553004606
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.240000053978292e-07,
"count": 1,
"self": 9.240000053978292e-07
},
"TrainerController._save_models": {
"total": 0.07626460400001633,
"count": 1,
"self": 0.0006752280000910105,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07558937599992532,
"count": 1,
"self": 0.07558937599992532
}
}
}
}
}
}
}