Nicolas852's picture
First commit
e130a90 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7976163029670715,
"min": 0.7588400840759277,
"max": 2.847287893295288,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7606.86669921875,
"min": 7345.572265625,
"max": 29159.07421875,
"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": 25.873119354248047,
"min": 0.570752739906311,
"max": 25.873119354248047,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 5045.25830078125,
"min": 110.72603607177734,
"max": 5229.498046875,
"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": 0.07073637239548534,
"min": 0.06145535350010237,
"max": 0.076596473509391,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2829454895819414,
"min": 0.25722461533201996,
"max": 0.382982367546955,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19619662205086036,
"min": 0.15709686565884004,
"max": 0.36841442158409193,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7847864882034414,
"min": 0.6283874626353602,
"max": 1.6916172215167213,
"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": 0.10404100000000001,
"min": 0.10404100000000001,
"max": 0.24594099999999997,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41616400000000003,
"min": 0.41616400000000003,
"max": 1.19258,
"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": 26.227272727272727,
"min": 4.318181818181818,
"max": 26.227272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1154.0,
"min": 190.0,
"max": 1425.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.227272727272727,
"min": 4.318181818181818,
"max": 26.227272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1154.0,
"min": 190.0,
"max": 1425.0,
"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": "1706584210",
"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": "1706584703"
},
"total": 493.42472342200017,
"count": 1,
"self": 0.4902028770002289,
"children": {
"run_training.setup": {
"total": 0.05614780399992014,
"count": 1,
"self": 0.05614780399992014
},
"TrainerController.start_learning": {
"total": 492.878372741,
"count": 1,
"self": 0.648619493995966,
"children": {
"TrainerController._reset_env": {
"total": 3.6938882669999202,
"count": 1,
"self": 3.6938882669999202
},
"TrainerController.advance": {
"total": 488.4403666920041,
"count": 18198,
"self": 0.31288512401556545,
"children": {
"env_step": {
"total": 488.1274815679885,
"count": 18198,
"self": 321.74268908498107,
"children": {
"SubprocessEnvManager._take_step": {
"total": 166.05998200201907,
"count": 18198,
"self": 1.6126151780399596,
"children": {
"TorchPolicy.evaluate": {
"total": 164.4473668239791,
"count": 18198,
"self": 164.4473668239791
}
}
},
"workers": {
"total": 0.3248104809883898,
"count": 18198,
"self": 0.0,
"children": {
"worker_root": {
"total": 491.5307334380075,
"count": 18198,
"is_parallel": true,
"self": 242.18682086498825,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005783513000096718,
"count": 1,
"is_parallel": true,
"self": 0.003638216000126704,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021452969999700144,
"count": 10,
"is_parallel": true,
"self": 0.0021452969999700144
}
}
},
"UnityEnvironment.step": {
"total": 0.045447438000110196,
"count": 1,
"is_parallel": true,
"self": 0.0006873170000289974,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004684650000399415,
"count": 1,
"is_parallel": true,
"self": 0.0004684650000399415
},
"communicator.exchange": {
"total": 0.042077282000036575,
"count": 1,
"is_parallel": true,
"self": 0.042077282000036575
},
"steps_from_proto": {
"total": 0.002214374000004682,
"count": 1,
"is_parallel": true,
"self": 0.00042559699954836105,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017887770004563208,
"count": 10,
"is_parallel": true,
"self": 0.0017887770004563208
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 249.34391257301922,
"count": 18197,
"is_parallel": true,
"self": 11.557235147029587,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.957063940012404,
"count": 18197,
"is_parallel": true,
"self": 5.957063940012404
},
"communicator.exchange": {
"total": 193.82865201600202,
"count": 18197,
"is_parallel": true,
"self": 193.82865201600202
},
"steps_from_proto": {
"total": 38.00096146997521,
"count": 18197,
"is_parallel": true,
"self": 7.250614650011357,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.750346819963852,
"count": 181970,
"is_parallel": true,
"self": 30.750346819963852
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 3.932399999939662e-05,
"count": 1,
"self": 3.932399999939662e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 482.0128587869915,
"count": 725545,
"is_parallel": true,
"self": 16.157991339958926,
"children": {
"process_trajectory": {
"total": 264.294073679034,
"count": 725545,
"is_parallel": true,
"self": 263.56443674003367,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7296369390003292,
"count": 4,
"is_parallel": true,
"self": 0.7296369390003292
}
}
},
"_update_policy": {
"total": 201.56079376799858,
"count": 90,
"is_parallel": true,
"self": 63.82007450600122,
"children": {
"TorchPPOOptimizer.update": {
"total": 137.74071926199736,
"count": 4587,
"is_parallel": true,
"self": 137.74071926199736
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09545896400004494,
"count": 1,
"self": 0.000994533000039155,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09446443100000579,
"count": 1,
"self": 0.09446443100000579
}
}
}
}
}
}
}