alessiodm's picture
First Push
92755bb
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9893222451210022,
"min": 0.9893222451210022,
"max": 2.874645709991455,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9446.048828125,
"min": 9446.048828125,
"max": 29470.8671875,
"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": 12.422520637512207,
"min": 0.18620654940605164,
"max": 12.422520637512207,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2422.3916015625,
"min": 36.12406921386719,
"max": 2501.215087890625,
"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": 0.06245495199055215,
"min": 0.06245495199055215,
"max": 0.07617799040916926,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2498198079622086,
"min": 0.2498198079622086,
"max": 0.3626077480408176,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19562417162837936,
"min": 0.11172186532263262,
"max": 0.2885244733124387,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7824966865135174,
"min": 0.4468874612905305,
"max": 1.4426223665621936,
"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": 24.84090909090909,
"min": 2.909090909090909,
"max": 24.84090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1093.0,
"min": 128.0,
"max": 1333.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.84090909090909,
"min": 2.909090909090909,
"max": 24.84090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1093.0,
"min": 128.0,
"max": 1333.0,
"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": "1698688605",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1698689053"
},
"total": 448.03642081099997,
"count": 1,
"self": 0.42524470299997574,
"children": {
"run_training.setup": {
"total": 0.07142888800001401,
"count": 1,
"self": 0.07142888800001401
},
"TrainerController.start_learning": {
"total": 447.53974722,
"count": 1,
"self": 0.49938386101757715,
"children": {
"TrainerController._reset_env": {
"total": 8.69803636100005,
"count": 1,
"self": 8.69803636100005
},
"TrainerController.advance": {
"total": 438.2546869279827,
"count": 18198,
"self": 0.24103547497543332,
"children": {
"env_step": {
"total": 438.01365145300724,
"count": 18198,
"self": 297.6081910760165,
"children": {
"SubprocessEnvManager._take_step": {
"total": 140.15105932699907,
"count": 18198,
"self": 1.353697145992328,
"children": {
"TorchPolicy.evaluate": {
"total": 138.79736218100675,
"count": 18198,
"self": 138.79736218100675
}
}
},
"workers": {
"total": 0.2544010499916567,
"count": 18198,
"self": 0.0,
"children": {
"worker_root": {
"total": 446.4905880550034,
"count": 18198,
"is_parallel": true,
"self": 220.39092314099764,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006024668999998539,
"count": 1,
"is_parallel": true,
"self": 0.004138319000048796,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018863499999497435,
"count": 10,
"is_parallel": true,
"self": 0.0018863499999497435
}
}
},
"UnityEnvironment.step": {
"total": 0.0454235869999593,
"count": 1,
"is_parallel": true,
"self": 0.0006732059998739715,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004092770000170276,
"count": 1,
"is_parallel": true,
"self": 0.0004092770000170276
},
"communicator.exchange": {
"total": 0.042437317999997504,
"count": 1,
"is_parallel": true,
"self": 0.042437317999997504
},
"steps_from_proto": {
"total": 0.0019037860000707951,
"count": 1,
"is_parallel": true,
"self": 0.00036690100012037874,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015368849999504164,
"count": 10,
"is_parallel": true,
"self": 0.0015368849999504164
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 226.09966491400576,
"count": 18197,
"is_parallel": true,
"self": 10.302312619993131,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.258046710011058,
"count": 18197,
"is_parallel": true,
"self": 5.258046710011058
},
"communicator.exchange": {
"total": 178.51704814599645,
"count": 18197,
"is_parallel": true,
"self": 178.51704814599645
},
"steps_from_proto": {
"total": 32.02225743800511,
"count": 18197,
"is_parallel": true,
"self": 5.746895734039867,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.275361703965245,
"count": 181970,
"is_parallel": true,
"self": 26.275361703965245
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011665699980767386,
"count": 1,
"self": 0.00011665699980767386,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 434.7208269860846,
"count": 457407,
"is_parallel": true,
"self": 9.509387199070147,
"children": {
"process_trajectory": {
"total": 244.79176706101464,
"count": 457407,
"is_parallel": true,
"self": 243.81317106901474,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9785959919998959,
"count": 4,
"is_parallel": true,
"self": 0.9785959919998959
}
}
},
"_update_policy": {
"total": 180.41967272599982,
"count": 90,
"is_parallel": true,
"self": 55.6812191709987,
"children": {
"TorchPPOOptimizer.update": {
"total": 124.73845355500112,
"count": 4584,
"is_parallel": true,
"self": 124.73845355500112
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08752341299987165,
"count": 1,
"self": 0.0008001949997833435,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08672321800008831,
"count": 1,
"self": 0.08672321800008831
}
}
}
}
}
}
}