aegis301's picture
First Push
28a311b verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9373725056648254,
"min": 0.9373725056648254,
"max": 2.8567698001861572,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8960.34375,
"min": 8960.34375,
"max": 29256.1796875,
"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": 13.534958839416504,
"min": 0.3880355954170227,
"max": 13.53939437866211,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2639.31689453125,
"min": 75.2789077758789,
"max": 2763.45361328125,
"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": 0.06844772887394784,
"min": 0.0654792258685227,
"max": 0.07320506425928804,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2737909154957914,
"min": 0.2619169034740908,
"max": 0.3542446590618912,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1778842614196679,
"min": 0.13680864188046304,
"max": 0.2670077978030724,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7115370456786716,
"min": 0.5472345675218522,
"max": 1.2565216906807002,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000007e-06,
"min": 8.082097306000007e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400003e-05,
"min": 3.232838922400003e-05,
"max": 0.0013851600382799997,
"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": 0.9617200000000001,
"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": 26.318181818181817,
"min": 3.977272727272727,
"max": 26.818181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1158.0,
"min": 175.0,
"max": 1464.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.318181818181817,
"min": 3.977272727272727,
"max": 26.818181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1158.0,
"min": 175.0,
"max": 1464.0,
"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": "1719146629",
"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=SnowballTarget2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1719147275"
},
"total": 646.4586889030002,
"count": 1,
"self": 0.4893667999999707,
"children": {
"run_training.setup": {
"total": 0.05963221800038809,
"count": 1,
"self": 0.05963221800038809
},
"TrainerController.start_learning": {
"total": 645.9096898849998,
"count": 1,
"self": 0.5336215339980299,
"children": {
"TrainerController._reset_env": {
"total": 2.187713354999687,
"count": 1,
"self": 2.187713354999687
},
"TrainerController.advance": {
"total": 643.0996930440024,
"count": 18200,
"self": 0.2712373780300368,
"children": {
"env_step": {
"total": 642.8284556659723,
"count": 18200,
"self": 488.2033908330568,
"children": {
"SubprocessEnvManager._take_step": {
"total": 154.35621402197648,
"count": 18200,
"self": 1.438196400938068,
"children": {
"TorchPolicy.evaluate": {
"total": 152.91801762103842,
"count": 18200,
"self": 152.91801762103842
}
}
},
"workers": {
"total": 0.26885081093905683,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 644.6512547880084,
"count": 18200,
"is_parallel": true,
"self": 428.14940397203145,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0021336479999263247,
"count": 1,
"is_parallel": true,
"self": 0.0006368729996211187,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001496775000305206,
"count": 10,
"is_parallel": true,
"self": 0.001496775000305206
}
}
},
"UnityEnvironment.step": {
"total": 0.036731633999806945,
"count": 1,
"is_parallel": true,
"self": 0.0006529729998874245,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000425662999987253,
"count": 1,
"is_parallel": true,
"self": 0.000425662999987253
},
"communicator.exchange": {
"total": 0.033683786999972654,
"count": 1,
"is_parallel": true,
"self": 0.033683786999972654
},
"steps_from_proto": {
"total": 0.001969210999959614,
"count": 1,
"is_parallel": true,
"self": 0.00040911300038715126,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015600979995724629,
"count": 10,
"is_parallel": true,
"self": 0.0015600979995724629
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 216.50185081597692,
"count": 18199,
"is_parallel": true,
"self": 9.97498804694078,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.16596072800894,
"count": 18199,
"is_parallel": true,
"self": 5.16596072800894
},
"communicator.exchange": {
"total": 168.85817742498466,
"count": 18199,
"is_parallel": true,
"self": 168.85817742498466
},
"steps_from_proto": {
"total": 32.50272461604254,
"count": 18199,
"is_parallel": true,
"self": 5.963658398248754,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.53906621779379,
"count": 181990,
"is_parallel": true,
"self": 26.53906621779379
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011829299955934403,
"count": 1,
"self": 0.00011829299955934403,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 637.7169280362014,
"count": 660507,
"is_parallel": true,
"self": 14.004112221922242,
"children": {
"process_trajectory": {
"total": 241.24017940027807,
"count": 660507,
"is_parallel": true,
"self": 240.66677854727823,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5734008529998391,
"count": 4,
"is_parallel": true,
"self": 0.5734008529998391
}
}
},
"_update_policy": {
"total": 382.47263641400104,
"count": 90,
"is_parallel": true,
"self": 146.86537762198532,
"children": {
"TorchPPOOptimizer.update": {
"total": 235.60725879201573,
"count": 15290,
"is_parallel": true,
"self": 235.60725879201573
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08854365900015182,
"count": 1,
"self": 0.0006690190002700547,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08787463999988177,
"count": 1,
"self": 0.08787463999988177
}
}
}
}
}
}
}