mrinaldi86's picture
First Push
c7fab2d verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8163169026374817,
"min": 0.8163169026374817,
"max": 2.8505136966705322,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7758.27587890625,
"min": 7758.27587890625,
"max": 29098.04296875,
"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": 13.144278526306152,
"min": 0.5633500814437866,
"max": 13.144278526306152,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2563.13427734375,
"min": 109.2899169921875,
"max": 2641.39111328125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06789151516168918,
"min": 0.06062554176063642,
"max": 0.07987414589749109,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2715660606467567,
"min": 0.24250216704254568,
"max": 0.3672115577672444,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19664542282036707,
"min": 0.14641978642811962,
"max": 0.29171447543536916,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7865816912814683,
"min": 0.5856791457124785,
"max": 1.3437715076348362,
"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": 26.704545454545453,
"min": 4.0,
"max": 26.704545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1175.0,
"min": 176.0,
"max": 1405.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.704545454545453,
"min": 4.0,
"max": 26.704545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1175.0,
"min": 176.0,
"max": 1405.0,
"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": "1739941107",
"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": "1739941535"
},
"total": 428.95051387,
"count": 1,
"self": 0.43656598999996277,
"children": {
"run_training.setup": {
"total": 0.022425176999945506,
"count": 1,
"self": 0.022425176999945506
},
"TrainerController.start_learning": {
"total": 428.4915227030001,
"count": 1,
"self": 0.3430646089941547,
"children": {
"TrainerController._reset_env": {
"total": 2.904690985000002,
"count": 1,
"self": 2.904690985000002
},
"TrainerController.advance": {
"total": 425.15533639800594,
"count": 18192,
"self": 0.36923603798038585,
"children": {
"env_step": {
"total": 302.9955516510139,
"count": 18192,
"self": 230.8255141069926,
"children": {
"SubprocessEnvManager._take_step": {
"total": 71.95872843201244,
"count": 18192,
"self": 1.2668982130086306,
"children": {
"TorchPolicy.evaluate": {
"total": 70.6918302190038,
"count": 18192,
"self": 70.6918302190038
}
}
},
"workers": {
"total": 0.2113091120088484,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 426.950159076016,
"count": 18192,
"is_parallel": true,
"self": 224.05440225100972,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005765016000054857,
"count": 1,
"is_parallel": true,
"self": 0.004010716000038883,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017543000000159736,
"count": 10,
"is_parallel": true,
"self": 0.0017543000000159736
}
}
},
"UnityEnvironment.step": {
"total": 0.07180248599991046,
"count": 1,
"is_parallel": true,
"self": 0.000662765999891235,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038505999998506013,
"count": 1,
"is_parallel": true,
"self": 0.00038505999998506013
},
"communicator.exchange": {
"total": 0.06876255300005596,
"count": 1,
"is_parallel": true,
"self": 0.06876255300005596
},
"steps_from_proto": {
"total": 0.001992106999978205,
"count": 1,
"is_parallel": true,
"self": 0.00043592799988800834,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015561790000901965,
"count": 10,
"is_parallel": true,
"self": 0.0015561790000901965
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 202.8957568250063,
"count": 18191,
"is_parallel": true,
"self": 9.701736720006807,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.363187407000851,
"count": 18191,
"is_parallel": true,
"self": 5.363187407000851
},
"communicator.exchange": {
"total": 156.11646657999552,
"count": 18191,
"is_parallel": true,
"self": 156.11646657999552
},
"steps_from_proto": {
"total": 31.714366118003113,
"count": 18191,
"is_parallel": true,
"self": 5.642910892008786,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.071455225994328,
"count": 181910,
"is_parallel": true,
"self": 26.071455225994328
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 121.79054870901166,
"count": 18192,
"self": 0.40356769401785186,
"children": {
"process_trajectory": {
"total": 26.892106958994646,
"count": 18192,
"self": 26.312729019994777,
"children": {
"RLTrainer._checkpoint": {
"total": 0.579377938999869,
"count": 4,
"self": 0.579377938999869
}
}
},
"_update_policy": {
"total": 94.49487405599916,
"count": 90,
"self": 37.78188228599777,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.712991770001395,
"count": 4587,
"self": 56.712991770001395
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3229998785391217e-06,
"count": 1,
"self": 1.3229998785391217e-06
},
"TrainerController._save_models": {
"total": 0.08842938800012234,
"count": 1,
"self": 0.0009380030001011619,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08749138500002118,
"count": 1,
"self": 0.08749138500002118
}
}
}
}
}
}
}