nlamot's picture
First Push
db5ef01
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8928791880607605,
"min": 0.887333333492279,
"max": 2.869736433029175,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8593.9619140625,
"min": 8593.9619140625,
"max": 29515.23828125,
"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": 13.072197914123535,
"min": 0.29536721110343933,
"max": 13.072197914123535,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2549.07861328125,
"min": 57.301239013671875,
"max": 2661.830078125,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06512467143415158,
"min": 0.059522127107529924,
"max": 0.07415758570805694,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26049868573660634,
"min": 0.2583463557524488,
"max": 0.3682584151352856,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18756353760174677,
"min": 0.12537180889151334,
"max": 0.28395300992563655,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7502541504069871,
"min": 0.5014872355660533,
"max": 1.4197650496281828,
"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": 25.318181818181817,
"min": 3.522727272727273,
"max": 25.795454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1114.0,
"min": 155.0,
"max": 1395.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.318181818181817,
"min": 3.522727272727273,
"max": 25.795454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1114.0,
"min": 155.0,
"max": 1395.0,
"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": "1703588259",
"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": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1703588731"
},
"total": 471.64524152599995,
"count": 1,
"self": 0.5544279500001039,
"children": {
"run_training.setup": {
"total": 0.052295106999963537,
"count": 1,
"self": 0.052295106999963537
},
"TrainerController.start_learning": {
"total": 471.0385184689999,
"count": 1,
"self": 0.606930220993604,
"children": {
"TrainerController._reset_env": {
"total": 3.5396257239999613,
"count": 1,
"self": 3.5396257239999613
},
"TrainerController.advance": {
"total": 466.7367942860061,
"count": 18215,
"self": 0.2907597350134665,
"children": {
"env_step": {
"total": 466.44603455099264,
"count": 18215,
"self": 305.8476101149837,
"children": {
"SubprocessEnvManager._take_step": {
"total": 160.28640382699973,
"count": 18215,
"self": 1.5352171249845696,
"children": {
"TorchPolicy.evaluate": {
"total": 158.75118670201516,
"count": 18215,
"self": 158.75118670201516
}
}
},
"workers": {
"total": 0.3120206090092097,
"count": 18215,
"self": 0.0,
"children": {
"worker_root": {
"total": 469.7273651029949,
"count": 18215,
"is_parallel": true,
"self": 230.00477434900063,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004683490000047641,
"count": 1,
"is_parallel": true,
"self": 0.0032550859998536907,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014284040001939502,
"count": 10,
"is_parallel": true,
"self": 0.0014284040001939502
}
}
},
"UnityEnvironment.step": {
"total": 0.03982307299997956,
"count": 1,
"is_parallel": true,
"self": 0.0007084400000394453,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00044568700002400874,
"count": 1,
"is_parallel": true,
"self": 0.00044568700002400874
},
"communicator.exchange": {
"total": 0.0362587079999912,
"count": 1,
"is_parallel": true,
"self": 0.0362587079999912
},
"steps_from_proto": {
"total": 0.0024102379999249024,
"count": 1,
"is_parallel": true,
"self": 0.00046425900006852316,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019459789998563792,
"count": 10,
"is_parallel": true,
"self": 0.0019459789998563792
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 239.72259075399427,
"count": 18214,
"is_parallel": true,
"self": 11.334130108009504,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.690063901001963,
"count": 18214,
"is_parallel": true,
"self": 5.690063901001963
},
"communicator.exchange": {
"total": 185.90888577599685,
"count": 18214,
"is_parallel": true,
"self": 185.90888577599685
},
"steps_from_proto": {
"total": 36.78951096898595,
"count": 18214,
"is_parallel": true,
"self": 6.867989412916245,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.921521556069706,
"count": 182140,
"is_parallel": true,
"self": 29.921521556069706
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001963240001714439,
"count": 1,
"self": 0.0001963240001714439,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 461.0143599530204,
"count": 671323,
"is_parallel": true,
"self": 14.508656393027536,
"children": {
"process_trajectory": {
"total": 257.1081091819933,
"count": 671323,
"is_parallel": true,
"self": 256.0956757139935,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0124334679998128,
"count": 4,
"is_parallel": true,
"self": 1.0124334679998128
}
}
},
"_update_policy": {
"total": 189.39759437799955,
"count": 90,
"is_parallel": true,
"self": 55.37572357200406,
"children": {
"TorchPPOOptimizer.update": {
"total": 134.0218708059955,
"count": 4581,
"is_parallel": true,
"self": 134.0218708059955
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1549719140000434,
"count": 1,
"self": 0.0014663100000689155,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15350560399997448,
"count": 1,
"self": 0.15350560399997448
}
}
}
}
}
}
}