kostas-c's picture
First Push
b87561a verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9843620657920837,
"min": 0.9843620657920837,
"max": 2.824025869369507,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9355.376953125,
"min": 9355.376953125,
"max": 28827.65625,
"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": 12.700132369995117,
"min": 0.5343734622001648,
"max": 12.700132369995117,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2476.52587890625,
"min": 103.66845703125,
"max": 2553.71875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0725985438509858,
"min": 0.06155698394714444,
"max": 0.07809543704078191,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2903941754039432,
"min": 0.2497409500824242,
"max": 0.3825066733281311,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19526107930669598,
"min": 0.12457066902653405,
"max": 0.2700650420259027,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7810443172267839,
"min": 0.4982826761061362,
"max": 1.3503252101295136,
"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": 25.363636363636363,
"min": 3.590909090909091,
"max": 25.363636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1116.0,
"min": 158.0,
"max": 1375.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.363636363636363,
"min": 3.590909090909091,
"max": 25.363636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1116.0,
"min": 158.0,
"max": 1375.0,
"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": "1764698584",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1764699007"
},
"total": 423.11912600799997,
"count": 1,
"self": 0.43463117500004955,
"children": {
"run_training.setup": {
"total": 0.026282881999918573,
"count": 1,
"self": 0.026282881999918573
},
"TrainerController.start_learning": {
"total": 422.658211951,
"count": 1,
"self": 0.3207839640142538,
"children": {
"TrainerController._reset_env": {
"total": 3.1301451850000603,
"count": 1,
"self": 3.1301451850000603
},
"TrainerController.advance": {
"total": 419.12223735098576,
"count": 18192,
"self": 0.3658318269860956,
"children": {
"env_step": {
"total": 303.5062678899957,
"count": 18192,
"self": 237.21592084101053,
"children": {
"SubprocessEnvManager._take_step": {
"total": 66.09057600498704,
"count": 18192,
"self": 1.1874347219740002,
"children": {
"TorchPolicy.evaluate": {
"total": 64.90314128301304,
"count": 18192,
"self": 64.90314128301304
}
}
},
"workers": {
"total": 0.19977104399811196,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 420.8736034210011,
"count": 18192,
"is_parallel": true,
"self": 212.30865339300772,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004309492999936992,
"count": 1,
"is_parallel": true,
"self": 0.002788891000136573,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015206019998004194,
"count": 10,
"is_parallel": true,
"self": 0.0015206019998004194
}
}
},
"UnityEnvironment.step": {
"total": 0.07322537799996098,
"count": 1,
"is_parallel": true,
"self": 0.0016501929998185005,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039414000002579996,
"count": 1,
"is_parallel": true,
"self": 0.00039414000002579996
},
"communicator.exchange": {
"total": 0.06695296500004133,
"count": 1,
"is_parallel": true,
"self": 0.06695296500004133
},
"steps_from_proto": {
"total": 0.0042280800000753516,
"count": 1,
"is_parallel": true,
"self": 0.0007245709999779137,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003503509000097438,
"count": 10,
"is_parallel": true,
"self": 0.003503509000097438
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 208.5649500279934,
"count": 18191,
"is_parallel": true,
"self": 9.95241002098885,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.327549299997145,
"count": 18191,
"is_parallel": true,
"self": 5.327549299997145
},
"communicator.exchange": {
"total": 158.31457114599732,
"count": 18191,
"is_parallel": true,
"self": 158.31457114599732
},
"steps_from_proto": {
"total": 34.97041956101009,
"count": 18191,
"is_parallel": true,
"self": 6.412726758025997,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.557692802984093,
"count": 181910,
"is_parallel": true,
"self": 28.557692802984093
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 115.25013763400398,
"count": 18192,
"self": 0.4147165489900999,
"children": {
"process_trajectory": {
"total": 25.155671956013975,
"count": 18192,
"self": 24.675575361014012,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4800965949999636,
"count": 4,
"self": 0.4800965949999636
}
}
},
"_update_policy": {
"total": 89.6797491289999,
"count": 90,
"self": 36.29023055100538,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.38951857799452,
"count": 4587,
"self": 53.38951857799452
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.8099997103418e-07,
"count": 1,
"self": 9.8099997103418e-07
},
"TrainerController._save_models": {
"total": 0.08504446999995707,
"count": 1,
"self": 0.0007001239999908648,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08434434599996621,
"count": 1,
"self": 0.08434434599996621
}
}
}
}
}
}
}