stevebubobot's picture
First Push
a0a549d verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7017340064048767,
"min": 0.6869953274726868,
"max": 2.8471484184265137,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6669.2802734375,
"min": 6669.2802734375,
"max": 29063.69140625,
"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": 13.077757835388184,
"min": 0.3702552318572998,
"max": 13.077757835388184,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2550.162841796875,
"min": 71.82951354980469,
"max": 2634.64306640625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07177025288504357,
"min": 0.06392580671395705,
"max": 0.07187399752864639,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2870810115401743,
"min": 0.262511374879407,
"max": 0.3590658780064105,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18811944324304078,
"min": 0.15187926231381282,
"max": 0.31046071955386334,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7524777729721631,
"min": 0.6075170492552513,
"max": 1.5059248436899746,
"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.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.Environment.CumulativeReward.mean": {
"value": 25.977272727272727,
"min": 4.0227272727272725,
"max": 25.977272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1143.0,
"min": 177.0,
"max": 1397.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.977272727272727,
"min": 4.0227272727272725,
"max": 25.977272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1143.0,
"min": 177.0,
"max": 1397.0,
"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": "1747835036",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1747835471"
},
"total": 435.51023472399993,
"count": 1,
"self": 0.43802594599992517,
"children": {
"run_training.setup": {
"total": 0.02412491699999464,
"count": 1,
"self": 0.02412491699999464
},
"TrainerController.start_learning": {
"total": 435.048083861,
"count": 1,
"self": 0.3772873310049931,
"children": {
"TrainerController._reset_env": {
"total": 3.57493234399999,
"count": 1,
"self": 3.57493234399999
},
"TrainerController.advance": {
"total": 431.0110510099949,
"count": 18192,
"self": 0.3970476619959413,
"children": {
"env_step": {
"total": 307.370429937002,
"count": 18192,
"self": 234.87852376999655,
"children": {
"SubprocessEnvManager._take_step": {
"total": 72.28295458800551,
"count": 18192,
"self": 1.2865660350121857,
"children": {
"TorchPolicy.evaluate": {
"total": 70.99638855299332,
"count": 18192,
"self": 70.99638855299332
}
}
},
"workers": {
"total": 0.20895157899991545,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 433.62439819599973,
"count": 18192,
"is_parallel": true,
"self": 227.7246350159977,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0068620199999713805,
"count": 1,
"is_parallel": true,
"self": 0.005366067000011299,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014959529999600818,
"count": 10,
"is_parallel": true,
"self": 0.0014959529999600818
}
}
},
"UnityEnvironment.step": {
"total": 0.03680619599998636,
"count": 1,
"is_parallel": true,
"self": 0.0006019560000254387,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038422699998363896,
"count": 1,
"is_parallel": true,
"self": 0.00038422699998363896
},
"communicator.exchange": {
"total": 0.03402118799999698,
"count": 1,
"is_parallel": true,
"self": 0.03402118799999698
},
"steps_from_proto": {
"total": 0.0017988249999802974,
"count": 1,
"is_parallel": true,
"self": 0.0003712480000785945,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001427576999901703,
"count": 10,
"is_parallel": true,
"self": 0.001427576999901703
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 205.89976318000203,
"count": 18191,
"is_parallel": true,
"self": 10.015379725000741,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.555919280002399,
"count": 18191,
"is_parallel": true,
"self": 5.555919280002399
},
"communicator.exchange": {
"total": 157.65824745799836,
"count": 18191,
"is_parallel": true,
"self": 157.65824745799836
},
"steps_from_proto": {
"total": 32.67021671700053,
"count": 18191,
"is_parallel": true,
"self": 5.946097515985684,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.724119201014844,
"count": 181910,
"is_parallel": true,
"self": 26.724119201014844
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 123.24357341099699,
"count": 18192,
"self": 0.45269531998923185,
"children": {
"process_trajectory": {
"total": 28.247985173007578,
"count": 18192,
"self": 27.82718675300748,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4207984200000965,
"count": 4,
"self": 0.4207984200000965
}
}
},
"_update_policy": {
"total": 94.54289291800018,
"count": 90,
"self": 38.4939267949992,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.04896612300098,
"count": 4587,
"self": 56.04896612300098
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0480000582901994e-06,
"count": 1,
"self": 1.0480000582901994e-06
},
"TrainerController._save_models": {
"total": 0.08481212800006688,
"count": 1,
"self": 0.000816320000012638,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08399580800005424,
"count": 1,
"self": 0.08399580800005424
}
}
}
}
}
}
}