axiden's picture
second Push
389bc67 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8993844985961914,
"min": 0.8993844985961914,
"max": 2.860459089279175,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8547.75,
"min": 8547.75,
"max": 29199.56640625,
"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": 12.92626667022705,
"min": 0.3667774796485901,
"max": 12.92626667022705,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2520.6220703125,
"min": 71.15483093261719,
"max": 2612.173828125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0705554111719168,
"min": 0.060890339804780744,
"max": 0.0756442453311334,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2822216446876672,
"min": 0.24356135921912297,
"max": 0.36084129472432075,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20439919391099143,
"min": 0.11367084978116385,
"max": 0.2817317682007948,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8175967756439657,
"min": 0.4546833991246554,
"max": 1.3651402078422845,
"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": 25.386363636363637,
"min": 3.159090909090909,
"max": 25.527272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1117.0,
"min": 139.0,
"max": 1404.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.386363636363637,
"min": 3.159090909090909,
"max": 25.527272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1117.0,
"min": 139.0,
"max": 1404.0,
"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": "1755363596",
"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": "1755364022"
},
"total": 426.5152645190001,
"count": 1,
"self": 0.43098038599987376,
"children": {
"run_training.setup": {
"total": 0.024653498000134277,
"count": 1,
"self": 0.024653498000134277
},
"TrainerController.start_learning": {
"total": 426.0596306350001,
"count": 1,
"self": 0.3289879399997062,
"children": {
"TrainerController._reset_env": {
"total": 2.7795416320000186,
"count": 1,
"self": 2.7795416320000186
},
"TrainerController.advance": {
"total": 422.85681544900035,
"count": 18192,
"self": 0.35444474397968406,
"children": {
"env_step": {
"total": 300.86061037600484,
"count": 18192,
"self": 231.84688226601725,
"children": {
"SubprocessEnvManager._take_step": {
"total": 68.81035536697732,
"count": 18192,
"self": 1.2506434249794438,
"children": {
"TorchPolicy.evaluate": {
"total": 67.55971194199788,
"count": 18192,
"self": 67.55971194199788
}
}
},
"workers": {
"total": 0.2033727430102772,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 424.70269406499233,
"count": 18192,
"is_parallel": true,
"self": 221.75494063699148,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006335907999982737,
"count": 1,
"is_parallel": true,
"self": 0.003982276999749956,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002353631000232781,
"count": 10,
"is_parallel": true,
"self": 0.002353631000232781
}
}
},
"UnityEnvironment.step": {
"total": 0.03399653700012095,
"count": 1,
"is_parallel": true,
"self": 0.0005977110001822439,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00037146199997550866,
"count": 1,
"is_parallel": true,
"self": 0.00037146199997550866
},
"communicator.exchange": {
"total": 0.031212979999963864,
"count": 1,
"is_parallel": true,
"self": 0.031212979999963864
},
"steps_from_proto": {
"total": 0.001814383999999336,
"count": 1,
"is_parallel": true,
"self": 0.0003721519999544398,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014422320000448963,
"count": 10,
"is_parallel": true,
"self": 0.0014422320000448963
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 202.94775342800085,
"count": 18191,
"is_parallel": true,
"self": 9.58738431097754,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.111419001992772,
"count": 18191,
"is_parallel": true,
"self": 5.111419001992772
},
"communicator.exchange": {
"total": 157.55973983402146,
"count": 18191,
"is_parallel": true,
"self": 157.55973983402146
},
"steps_from_proto": {
"total": 30.689210281009082,
"count": 18191,
"is_parallel": true,
"self": 5.304709171036848,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.384501109972234,
"count": 181910,
"is_parallel": true,
"self": 25.384501109972234
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 121.64176032901582,
"count": 18192,
"self": 0.38914000501449664,
"children": {
"process_trajectory": {
"total": 26.735136381001894,
"count": 18192,
"self": 26.360140636002143,
"children": {
"RLTrainer._checkpoint": {
"total": 0.37499574499975097,
"count": 4,
"self": 0.37499574499975097
}
}
},
"_update_policy": {
"total": 94.51748394299943,
"count": 90,
"self": 39.786508353986164,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.73097558901327,
"count": 4587,
"self": 54.73097558901327
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.550001323077595e-07,
"count": 1,
"self": 9.550001323077595e-07
},
"TrainerController._save_models": {
"total": 0.09428465899986804,
"count": 1,
"self": 0.000919028999760485,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09336563000010756,
"count": 1,
"self": 0.09336563000010756
}
}
}
}
}
}
}