arjunamate's picture
Second Push
43d93cd verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.031793475151062,
"min": 1.0097428560256958,
"max": 2.8327786922454834,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9806.1650390625,
"min": 9806.1650390625,
"max": 28917.00390625,
"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": 13.39430046081543,
"min": 0.4049510359764099,
"max": 13.39430046081543,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2611.888671875,
"min": 78.56050109863281,
"max": 2717.641845703125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06770996948790865,
"min": 0.06338850121748835,
"max": 0.07710218002908982,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2708398779516346,
"min": 0.2535540048699534,
"max": 0.3834374881839989,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18384962371897462,
"min": 0.12493921079280257,
"max": 0.3188552150101054,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7353984948758985,
"min": 0.4997568431712103,
"max": 1.5567299042846643,
"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": 26.613636363636363,
"min": 3.840909090909091,
"max": 26.613636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1171.0,
"min": 169.0,
"max": 1446.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.613636363636363,
"min": 3.840909090909091,
"max": 26.613636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1171.0,
"min": 169.0,
"max": 1446.0,
"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": "1771235592",
"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=SnowballTarget2 --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": "1771236116"
},
"total": 523.963878904,
"count": 1,
"self": 0.4770405120002579,
"children": {
"run_training.setup": {
"total": 0.03891777099988758,
"count": 1,
"self": 0.03891777099988758
},
"TrainerController.start_learning": {
"total": 523.4479206209999,
"count": 1,
"self": 0.43900507999751426,
"children": {
"TrainerController._reset_env": {
"total": 2.405319562999921,
"count": 1,
"self": 2.405319562999921
},
"TrainerController.advance": {
"total": 520.1848365720025,
"count": 18192,
"self": 0.4309070269584936,
"children": {
"env_step": {
"total": 371.3020106790343,
"count": 18192,
"self": 288.39580851905407,
"children": {
"SubprocessEnvManager._take_step": {
"total": 82.64306480999016,
"count": 18192,
"self": 1.4113672499995573,
"children": {
"TorchPolicy.evaluate": {
"total": 81.23169755999061,
"count": 18192,
"self": 81.23169755999061
}
}
},
"workers": {
"total": 0.26313734999007465,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 520.7289981980091,
"count": 18192,
"is_parallel": true,
"self": 267.34545497201907,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003138624000030177,
"count": 1,
"is_parallel": true,
"self": 0.0008645339999020507,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002274090000128126,
"count": 10,
"is_parallel": true,
"self": 0.002274090000128126
}
}
},
"UnityEnvironment.step": {
"total": 0.03977024599998913,
"count": 1,
"is_parallel": true,
"self": 0.0005931989996952325,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042645000007723866,
"count": 1,
"is_parallel": true,
"self": 0.00042645000007723866
},
"communicator.exchange": {
"total": 0.03667198300013297,
"count": 1,
"is_parallel": true,
"self": 0.03667198300013297
},
"steps_from_proto": {
"total": 0.0020786140000836895,
"count": 1,
"is_parallel": true,
"self": 0.0003909450001629011,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016876689999207883,
"count": 10,
"is_parallel": true,
"self": 0.0016876689999207883
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 253.38354322599002,
"count": 18191,
"is_parallel": true,
"self": 11.665370154996253,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.306499689992961,
"count": 18191,
"is_parallel": true,
"self": 6.306499689992961
},
"communicator.exchange": {
"total": 192.6655155389999,
"count": 18191,
"is_parallel": true,
"self": 192.6655155389999
},
"steps_from_proto": {
"total": 42.74615784200091,
"count": 18191,
"is_parallel": true,
"self": 7.410027365939868,
"children": {
"_process_rank_one_or_two_observation": {
"total": 35.336130476061044,
"count": 181910,
"is_parallel": true,
"self": 35.336130476061044
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 148.4519188660097,
"count": 18192,
"self": 0.5264141030054361,
"children": {
"process_trajectory": {
"total": 32.0468363040045,
"count": 18192,
"self": 30.215858211004615,
"children": {
"RLTrainer._checkpoint": {
"total": 1.8309780929998851,
"count": 4,
"self": 1.8309780929998851
}
}
},
"_update_policy": {
"total": 115.87866845899975,
"count": 90,
"self": 41.38713840200717,
"children": {
"TorchPPOOptimizer.update": {
"total": 74.49153005699259,
"count": 4587,
"self": 74.49153005699259
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.539999155094847e-07,
"count": 1,
"self": 9.539999155094847e-07
},
"TrainerController._save_models": {
"total": 0.41875845200002004,
"count": 1,
"self": 0.007750537999982043,
"children": {
"RLTrainer._checkpoint": {
"total": 0.411007914000038,
"count": 1,
"self": 0.411007914000038
}
}
}
}
}
}
}