wladimir's picture
First Push
662de08 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7305570244789124,
"min": 0.7218949198722839,
"max": 2.8611643314361572,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7079.828125,
"min": 7079.828125,
"max": 29301.18359375,
"count": 50
},
"SnowballTarget.Step.mean": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Step.sum": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.951395988464355,
"min": 0.3554496467113495,
"max": 13.972651481628418,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2860.0361328125,
"min": 68.95722961425781,
"max": 2860.0361328125,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06844273939314435,
"min": 0.0624090680370436,
"max": 0.074118411009027,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3422136969657218,
"min": 0.2615050502299496,
"max": 0.35716445213800074,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.16314536089406292,
"min": 0.11958101002280327,
"max": 0.2681680616210489,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8157268044703146,
"min": 0.4783240400912131,
"max": 1.216318077550215,
"count": 50
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 3.0528989824000028e-06,
"min": 3.0528989824000028e-06,
"max": 0.0002967528010824,
"count": 50
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.5264494912000015e-05,
"min": 1.5264494912000015e-05,
"max": 0.0014540640153119996,
"count": 50
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.1010176,
"min": 0.1010176,
"max": 0.19891760000000003,
"count": 50
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.505088,
"min": 0.41199040000000003,
"max": 0.984688,
"count": 50
},
"SnowballTarget.Policy.Beta.mean": {
"value": 6.0778240000000044e-05,
"min": 6.0778240000000044e-05,
"max": 0.00494598824,
"count": 50
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0003038912000000002,
"min": 0.0003038912000000002,
"max": 0.0242359312,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 27.2,
"min": 3.409090909090909,
"max": 27.6,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1496.0,
"min": 150.0,
"max": 1518.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 27.2,
"min": 3.409090909090909,
"max": 27.6,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1496.0,
"min": 150.0,
"max": 1518.0,
"count": 50
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1708038499",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1708039736"
},
"total": 1236.201066388,
"count": 1,
"self": 0.43544640000027357,
"children": {
"run_training.setup": {
"total": 0.051028324000071734,
"count": 1,
"self": 0.051028324000071734
},
"TrainerController.start_learning": {
"total": 1235.7145916639997,
"count": 1,
"self": 1.3771530910048568,
"children": {
"TrainerController._reset_env": {
"total": 2.23025210600008,
"count": 1,
"self": 2.23025210600008
},
"TrainerController.advance": {
"total": 1231.985199457995,
"count": 45476,
"self": 0.6375975549972281,
"children": {
"env_step": {
"total": 1231.3476019029977,
"count": 45476,
"self": 853.3624495590007,
"children": {
"SubprocessEnvManager._take_step": {
"total": 377.30211580399464,
"count": 45476,
"self": 3.5416961910125337,
"children": {
"TorchPolicy.evaluate": {
"total": 373.7604196129821,
"count": 45476,
"self": 373.7604196129821
}
}
},
"workers": {
"total": 0.6830365400023766,
"count": 45476,
"self": 0.0,
"children": {
"worker_root": {
"total": 1232.9955987259762,
"count": 45476,
"is_parallel": true,
"self": 698.2870175889993,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0021927940001660318,
"count": 1,
"is_parallel": true,
"self": 0.0007042889999411273,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014885050002249045,
"count": 10,
"is_parallel": true,
"self": 0.0014885050002249045
}
}
},
"UnityEnvironment.step": {
"total": 0.039752307000071596,
"count": 1,
"is_parallel": true,
"self": 0.0006199870001637464,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00043963100006294553,
"count": 1,
"is_parallel": true,
"self": 0.00043963100006294553
},
"communicator.exchange": {
"total": 0.03673621300004015,
"count": 1,
"is_parallel": true,
"self": 0.03673621300004015
},
"steps_from_proto": {
"total": 0.001956475999804752,
"count": 1,
"is_parallel": true,
"self": 0.0003864949997023359,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015699810001024161,
"count": 10,
"is_parallel": true,
"self": 0.0015699810001024161
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 534.7085811369768,
"count": 45475,
"is_parallel": true,
"self": 25.856902703059177,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 12.996769818960502,
"count": 45475,
"is_parallel": true,
"self": 12.996769818960502
},
"communicator.exchange": {
"total": 414.2704129009951,
"count": 45475,
"is_parallel": true,
"self": 414.2704129009951
},
"steps_from_proto": {
"total": 81.58449571396204,
"count": 45475,
"is_parallel": true,
"self": 14.897867056988616,
"children": {
"_process_rank_one_or_two_observation": {
"total": 66.68662865697343,
"count": 454750,
"is_parallel": true,
"self": 66.68662865697343
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00019756000028792187,
"count": 1,
"self": 0.00019756000028792187,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 1218.7511559329391,
"count": 1627478,
"is_parallel": true,
"self": 33.68630257197833,
"children": {
"process_trajectory": {
"total": 581.9410753819643,
"count": 1627478,
"is_parallel": true,
"self": 579.8221941829645,
"children": {
"RLTrainer._checkpoint": {
"total": 2.1188811989998158,
"count": 10,
"is_parallel": true,
"self": 2.1188811989998158
}
}
},
"_update_policy": {
"total": 603.1237779789965,
"count": 227,
"is_parallel": true,
"self": 187.33673080898143,
"children": {
"TorchPPOOptimizer.update": {
"total": 415.78704717001506,
"count": 19290,
"is_parallel": true,
"self": 415.78704717001506
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12178944899960698,
"count": 1,
"self": 0.0014115619997028261,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12037788699990415,
"count": 1,
"self": 0.12037788699990415
}
}
}
}
}
}
}