ed-butcher's picture
First Push
ade74ea verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0647257566452026,
"min": 1.0647257566452026,
"max": 2.8649089336395264,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10166.001953125,
"min": 10166.001953125,
"max": 29339.53125,
"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": 12.036871910095215,
"min": 0.4963882267475128,
"max": 12.036871910095215,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2347.18994140625,
"min": 96.29931640625,
"max": 2438.467529296875,
"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.Losses.PolicyLoss.mean": {
"value": 0.06755766737007755,
"min": 0.062202054887166014,
"max": 0.07277875123006251,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2702306694803102,
"min": 0.24880821954866406,
"max": 0.35757549909313263,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1893152803840006,
"min": 0.14494471892933636,
"max": 0.26868163553230906,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7572611215360024,
"min": 0.5797788757173454,
"max": 1.3209324972886667,
"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.CumulativeReward.mean": {
"value": 23.40909090909091,
"min": 4.090909090909091,
"max": 23.78181818181818,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1030.0,
"min": 180.0,
"max": 1308.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.40909090909091,
"min": 4.090909090909091,
"max": 23.78181818181818,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1030.0,
"min": 180.0,
"max": 1308.0,
"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": "1714225685",
"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=SnowballTarget1 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1714226180"
},
"total": 495.285337131,
"count": 1,
"self": 0.4350273070001549,
"children": {
"run_training.setup": {
"total": 0.05466718899992884,
"count": 1,
"self": 0.05466718899992884
},
"TrainerController.start_learning": {
"total": 494.7956426349999,
"count": 1,
"self": 0.6994613460144592,
"children": {
"TrainerController._reset_env": {
"total": 2.904392592000022,
"count": 1,
"self": 2.904392592000022
},
"TrainerController.advance": {
"total": 491.0948362379854,
"count": 18200,
"self": 0.3626260189871573,
"children": {
"env_step": {
"total": 490.73221021899826,
"count": 18200,
"self": 320.8954059760192,
"children": {
"SubprocessEnvManager._take_step": {
"total": 169.4840609809678,
"count": 18200,
"self": 1.7196094989749326,
"children": {
"TorchPolicy.evaluate": {
"total": 167.76445148199286,
"count": 18200,
"self": 167.76445148199286
}
}
},
"workers": {
"total": 0.35274326201124495,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 493.3280625829748,
"count": 18200,
"is_parallel": true,
"self": 242.38598881698863,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005596535999984553,
"count": 1,
"is_parallel": true,
"self": 0.004009741000345457,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015867949996390962,
"count": 10,
"is_parallel": true,
"self": 0.0015867949996390962
}
}
},
"UnityEnvironment.step": {
"total": 0.074236658000018,
"count": 1,
"is_parallel": true,
"self": 0.0006722699999954784,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004734900001039932,
"count": 1,
"is_parallel": true,
"self": 0.0004734900001039932
},
"communicator.exchange": {
"total": 0.06865793399992981,
"count": 1,
"is_parallel": true,
"self": 0.06865793399992981
},
"steps_from_proto": {
"total": 0.004432963999988715,
"count": 1,
"is_parallel": true,
"self": 0.0026000620002832875,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018329019997054274,
"count": 10,
"is_parallel": true,
"self": 0.0018329019997054274
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 250.94207376598615,
"count": 18199,
"is_parallel": true,
"self": 11.316994766955077,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.236355841012255,
"count": 18199,
"is_parallel": true,
"self": 6.236355841012255
},
"communicator.exchange": {
"total": 195.74389543601978,
"count": 18199,
"is_parallel": true,
"self": 195.74389543601978
},
"steps_from_proto": {
"total": 37.644827721999036,
"count": 18199,
"is_parallel": true,
"self": 7.404575926010466,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.24025179598857,
"count": 181990,
"is_parallel": true,
"self": 30.24025179598857
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013829099998474703,
"count": 1,
"self": 0.00013829099998474703,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 484.95513632098573,
"count": 758180,
"is_parallel": true,
"self": 16.168489005953006,
"children": {
"process_trajectory": {
"total": 272.1906945640335,
"count": 758180,
"is_parallel": true,
"self": 271.3809363480334,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8097582160000911,
"count": 4,
"is_parallel": true,
"self": 0.8097582160000911
}
}
},
"_update_policy": {
"total": 196.59595275099923,
"count": 90,
"is_parallel": true,
"self": 55.80620713100461,
"children": {
"TorchPPOOptimizer.update": {
"total": 140.78974561999462,
"count": 4587,
"is_parallel": true,
"self": 140.78974561999462
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09681416800003717,
"count": 1,
"self": 0.0009531579999020323,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09586101000013514,
"count": 1,
"self": 0.09586101000013514
}
}
}
}
}
}
}