pabloyesteb's picture
Primera subida
5524f91
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.4326049089431763,
"min": 1.4267691373825073,
"max": 2.890326738357544,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 13788.822265625,
"min": 13788.822265625,
"max": 29660.625,
"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": 10.447596549987793,
"min": 0.12211652845144272,
"max": 10.447596549987793,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2141.75732421875,
"min": 23.69060707092285,
"max": 2141.75732421875,
"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.Environment.CumulativeReward.mean": {
"value": 23.272727272727273,
"min": 2.581818181818182,
"max": 23.818181818181817,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1280.0,
"min": 116.0,
"max": 1310.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.272727272727273,
"min": 2.581818181818182,
"max": 23.818181818181817,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1280.0,
"min": 116.0,
"max": 1310.0,
"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
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06794260218491156,
"min": 0.06266398389587023,
"max": 0.0763079910264991,
"count": 30
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.06794260218491156,
"min": 0.06266398389587023,
"max": 0.0763079910264991,
"count": 30
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22742961585521698,
"min": 0.07841670646270116,
"max": 0.2775347908337911,
"count": 30
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.22742961585521698,
"min": 0.07841670646270116,
"max": 0.2775347908337911,
"count": 30
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 9.652896782399993e-06,
"min": 9.652896782399993e-06,
"max": 0.0002903376032208,
"count": 30
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 9.652896782399993e-06,
"min": 9.652896782399993e-06,
"max": 0.0002903376032208,
"count": 30
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.1032176,
"min": 0.1032176,
"max": 0.19677920000000002,
"count": 30
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.1032176,
"min": 0.1032176,
"max": 0.19677920000000002,
"count": 30
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001705582399999999,
"min": 0.0001705582399999999,
"max": 0.00483928208,
"count": 30
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0001705582399999999,
"min": 0.0001705582399999999,
"max": 0.00483928208,
"count": 30
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1692471646",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1692472993"
},
"total": 1346.4619236789995,
"count": 1,
"self": 0.7904559149997112,
"children": {
"run_training.setup": {
"total": 0.0695312500001819,
"count": 1,
"self": 0.0695312500001819
},
"TrainerController.start_learning": {
"total": 1345.6019365139996,
"count": 1,
"self": 1.5879936779952004,
"children": {
"TrainerController._reset_env": {
"total": 4.928958944999977,
"count": 1,
"self": 4.928958944999977
},
"TrainerController.advance": {
"total": 1338.9268934820038,
"count": 45472,
"self": 0.8328126520373189,
"children": {
"env_step": {
"total": 1338.0940808299665,
"count": 45472,
"self": 1021.545251526954,
"children": {
"SubprocessEnvManager._take_step": {
"total": 315.7181509330144,
"count": 45472,
"self": 5.365663437006333,
"children": {
"TorchPolicy.evaluate": {
"total": 310.35248749600805,
"count": 45472,
"self": 310.35248749600805
}
}
},
"workers": {
"total": 0.8306783699981679,
"count": 45472,
"self": 0.0,
"children": {
"worker_root": {
"total": 1341.5000671918947,
"count": 45472,
"is_parallel": true,
"self": 649.3499547417941,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007126122000045143,
"count": 1,
"is_parallel": true,
"self": 0.004601272999934736,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0025248490001104074,
"count": 10,
"is_parallel": true,
"self": 0.0025248490001104074
}
}
},
"UnityEnvironment.step": {
"total": 0.04650596300007237,
"count": 1,
"is_parallel": true,
"self": 0.000710006000190333,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005335739997462952,
"count": 1,
"is_parallel": true,
"self": 0.0005335739997462952
},
"communicator.exchange": {
"total": 0.04271919299981164,
"count": 1,
"is_parallel": true,
"self": 0.04271919299981164
},
"steps_from_proto": {
"total": 0.0025431900003241026,
"count": 1,
"is_parallel": true,
"self": 0.0005836969994561514,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001959493000867951,
"count": 10,
"is_parallel": true,
"self": 0.001959493000867951
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 692.1501124501006,
"count": 45471,
"is_parallel": true,
"self": 28.66509968013952,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 15.045883582045917,
"count": 45471,
"is_parallel": true,
"self": 15.045883582045917
},
"communicator.exchange": {
"total": 544.6678777069947,
"count": 45471,
"is_parallel": true,
"self": 544.6678777069947
},
"steps_from_proto": {
"total": 103.77125148092045,
"count": 45471,
"is_parallel": true,
"self": 19.4031287098569,
"children": {
"_process_rank_one_or_two_observation": {
"total": 84.36812277106355,
"count": 454710,
"is_parallel": true,
"self": 84.36812277106355
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00010915199982264312,
"count": 1,
"self": 0.00010915199982264312,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 1322.2221411636929,
"count": 1789745,
"is_parallel": true,
"self": 43.33284099568482,
"children": {
"process_trajectory": {
"total": 976.6379704540113,
"count": 1789745,
"is_parallel": true,
"self": 974.3473603650118,
"children": {
"RLTrainer._checkpoint": {
"total": 2.2906100889995287,
"count": 10,
"is_parallel": true,
"self": 2.2906100889995287
}
}
},
"_update_policy": {
"total": 302.2513297139967,
"count": 30,
"is_parallel": true,
"self": 163.05474629695664,
"children": {
"TorchPPOOptimizer.update": {
"total": 139.19658341704007,
"count": 11277,
"is_parallel": true,
"self": 139.19658341704007
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.15798125700075616,
"count": 1,
"self": 0.0007658980002815952,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15721535900047456,
"count": 1,
"self": 0.15721535900047456
}
}
}
}
}
}
}