udonhef2bmad's picture
First Push
7f4f33a verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8579821586608887,
"min": 0.8434503674507141,
"max": 2.8511881828308105,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8154.2626953125,
"min": 8154.2626953125,
"max": 29104.9296875,
"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": 11.80886173248291,
"min": 0.35181403160095215,
"max": 11.80886173248291,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2302.72802734375,
"min": 68.25192260742188,
"max": 2403.8173828125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06965506623850623,
"min": 0.06263017403775936,
"max": 0.073363498387848,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2786202649540249,
"min": 0.2550006259463022,
"max": 0.35384714796493755,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18276699687189918,
"min": 0.10173362966024262,
"max": 0.27812326487665084,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7310679874875967,
"min": 0.40693451864097047,
"max": 1.3617967878486594,
"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": 23.272727272727273,
"min": 3.022727272727273,
"max": 23.272727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1024.0,
"min": 133.0,
"max": 1280.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.272727272727273,
"min": 3.022727272727273,
"max": 23.272727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1024.0,
"min": 133.0,
"max": 1280.0,
"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": "1741117210",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1741117637"
},
"total": 427.72948820299985,
"count": 1,
"self": 0.43963612099992133,
"children": {
"run_training.setup": {
"total": 0.022562835999906383,
"count": 1,
"self": 0.022562835999906383
},
"TrainerController.start_learning": {
"total": 427.267289246,
"count": 1,
"self": 0.3577728120131951,
"children": {
"TrainerController._reset_env": {
"total": 3.330074925999952,
"count": 1,
"self": 3.330074925999952
},
"TrainerController.advance": {
"total": 423.4869644999868,
"count": 18192,
"self": 0.35978264998311715,
"children": {
"env_step": {
"total": 298.69246841200334,
"count": 18192,
"self": 227.765789487985,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.7103809549908,
"count": 18192,
"self": 1.2239440399879413,
"children": {
"TorchPolicy.evaluate": {
"total": 69.48643691500286,
"count": 18192,
"self": 69.48643691500286
}
}
},
"workers": {
"total": 0.2162979690275506,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 425.7087544389826,
"count": 18192,
"is_parallel": true,
"self": 225.6328486719857,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005822228999932122,
"count": 1,
"is_parallel": true,
"self": 0.00421561599978304,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001606613000149082,
"count": 10,
"is_parallel": true,
"self": 0.001606613000149082
}
}
},
"UnityEnvironment.step": {
"total": 0.056172244999970644,
"count": 1,
"is_parallel": true,
"self": 0.0005733930000815235,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003882249999378473,
"count": 1,
"is_parallel": true,
"self": 0.0003882249999378473
},
"communicator.exchange": {
"total": 0.05356843599997774,
"count": 1,
"is_parallel": true,
"self": 0.05356843599997774
},
"steps_from_proto": {
"total": 0.0016421909999735362,
"count": 1,
"is_parallel": true,
"self": 0.0003093330000183414,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013328579999551948,
"count": 10,
"is_parallel": true,
"self": 0.0013328579999551948
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 200.07590576699693,
"count": 18191,
"is_parallel": true,
"self": 9.608214555020595,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.210582046986588,
"count": 18191,
"is_parallel": true,
"self": 5.210582046986588
},
"communicator.exchange": {
"total": 154.5791771009948,
"count": 18191,
"is_parallel": true,
"self": 154.5791771009948
},
"steps_from_proto": {
"total": 30.677932063994945,
"count": 18191,
"is_parallel": true,
"self": 5.502907528986839,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.175024535008106,
"count": 181910,
"is_parallel": true,
"self": 25.175024535008106
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 124.43471343800036,
"count": 18192,
"self": 0.4618846049883132,
"children": {
"process_trajectory": {
"total": 26.920013139013918,
"count": 18192,
"self": 26.361735004013667,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5582781350002506,
"count": 4,
"self": 0.5582781350002506
}
}
},
"_update_policy": {
"total": 97.05281569399813,
"count": 90,
"self": 38.75817701399285,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.29463868000528,
"count": 4587,
"self": 58.29463868000528
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.860000318440143e-07,
"count": 1,
"self": 9.860000318440143e-07
},
"TrainerController._save_models": {
"total": 0.09247602200002802,
"count": 1,
"self": 0.0009940280001501378,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09148199399987789,
"count": 1,
"self": 0.09148199399987789
}
}
}
}
}
}
}