code1phoenix's picture
First Push
c62f4a4 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0669304132461548,
"min": 1.0664451122283936,
"max": 2.8499834537506104,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10140.1064453125,
"min": 10140.1064453125,
"max": 29092.630859375,
"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": 12.846659660339355,
"min": 0.25912633538246155,
"max": 12.846659660339355,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2505.0986328125,
"min": 50.270511627197266,
"max": 2608.966796875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07023874698843072,
"min": 0.059253919316924836,
"max": 0.07710473640369908,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28095498795372287,
"min": 0.23701567726769934,
"max": 0.35370715836396294,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2136608739840049,
"min": 0.12960525659511013,
"max": 0.2983144864147785,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8546434959360196,
"min": 0.5184210263804405,
"max": 1.4915724320738923,
"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": 25.204545454545453,
"min": 3.522727272727273,
"max": 25.295454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1109.0,
"min": 155.0,
"max": 1383.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.204545454545453,
"min": 3.522727272727273,
"max": 25.295454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1109.0,
"min": 155.0,
"max": 1383.0,
"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": "1773882995",
"python_version": "3.10.13 (main, Sep 11 2023, 13:44:35) [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 --force",
"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": "1773883448"
},
"total": 452.8876958159999,
"count": 1,
"self": 0.4305091900005209,
"children": {
"run_training.setup": {
"total": 0.022213899999769637,
"count": 1,
"self": 0.022213899999769637
},
"TrainerController.start_learning": {
"total": 452.4349727259996,
"count": 1,
"self": 0.3829435549514528,
"children": {
"TrainerController._reset_env": {
"total": 2.1849690730005022,
"count": 1,
"self": 2.1849690730005022
},
"TrainerController.advance": {
"total": 449.78612203604825,
"count": 18192,
"self": 0.40256697202949,
"children": {
"env_step": {
"total": 328.45721544901244,
"count": 18192,
"self": 255.28124132700395,
"children": {
"SubprocessEnvManager._take_step": {
"total": 72.95362465697781,
"count": 18192,
"self": 1.323621803971946,
"children": {
"TorchPolicy.evaluate": {
"total": 71.63000285300586,
"count": 18192,
"self": 71.63000285300586
}
}
},
"workers": {
"total": 0.22234946503067476,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 450.5245498540053,
"count": 18192,
"is_parallel": true,
"self": 226.27875806008433,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020752079999510897,
"count": 1,
"is_parallel": true,
"self": 0.0006778540009690914,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013973539989819983,
"count": 10,
"is_parallel": true,
"self": 0.0013973539989819983
}
}
},
"UnityEnvironment.step": {
"total": 0.036999822000325366,
"count": 1,
"is_parallel": true,
"self": 0.0006059699999241275,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041153199981636135,
"count": 1,
"is_parallel": true,
"self": 0.00041153199981636135
},
"communicator.exchange": {
"total": 0.03399942200030637,
"count": 1,
"is_parallel": true,
"self": 0.03399942200030637
},
"steps_from_proto": {
"total": 0.00198289800027851,
"count": 1,
"is_parallel": true,
"self": 0.0003886320037054247,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015942659965730854,
"count": 10,
"is_parallel": true,
"self": 0.0015942659965730854
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 224.24579179392094,
"count": 18191,
"is_parallel": true,
"self": 10.457083806854826,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.473899215020538,
"count": 18191,
"is_parallel": true,
"self": 5.473899215020538
},
"communicator.exchange": {
"total": 170.6107444960171,
"count": 18191,
"is_parallel": true,
"self": 170.6107444960171
},
"steps_from_proto": {
"total": 37.704064276028475,
"count": 18191,
"is_parallel": true,
"self": 6.838536552854748,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.865527723173727,
"count": 181910,
"is_parallel": true,
"self": 30.865527723173727
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 120.92633961500633,
"count": 18192,
"self": 0.45888229205320386,
"children": {
"process_trajectory": {
"total": 27.25952938294813,
"count": 18192,
"self": 26.808468882947636,
"children": {
"RLTrainer._checkpoint": {
"total": 0.45106050000049436,
"count": 4,
"self": 0.45106050000049436
}
}
},
"_update_policy": {
"total": 93.20792794000499,
"count": 90,
"self": 37.10431223898195,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.103615701023045,
"count": 4587,
"self": 56.103615701023045
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.959996193880215e-07,
"count": 1,
"self": 8.959996193880215e-07
},
"TrainerController._save_models": {
"total": 0.08093716599978507,
"count": 1,
"self": 0.0007908099996711826,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08014635600011388,
"count": 1,
"self": 0.08014635600011388
}
}
}
}
}
}
}