letaldir's picture
First Push
16271a9 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.5640982389450073,
"min": 0.5248498320579529,
"max": 0.8223243355751038,
"count": 80
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 5361.18994140625,
"min": 5036.2109375,
"max": 8394.287109375,
"count": 80
},
"SnowballTarget.Step.mean": {
"value": 999992.0,
"min": 209936.0,
"max": 999992.0,
"count": 80
},
"SnowballTarget.Step.sum": {
"value": 999992.0,
"min": 209936.0,
"max": 999992.0,
"count": 80
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 14.082098960876465,
"min": 13.011780738830566,
"max": 14.145417213439941,
"count": 80
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2746.00927734375,
"min": 2535.1767578125,
"max": 2899.810546875,
"count": 80
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06788015230153642,
"min": 0.059591184976549506,
"max": 0.07591775905501552,
"count": 80
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2715206092061457,
"min": 0.23836473990619803,
"max": 0.3694794026817487,
"count": 80
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.15987854301199025,
"min": 0.15198761747017797,
"max": 0.2099796385303432,
"count": 80
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.639514172047961,
"min": 0.6079504698807119,
"max": 1.003449835613662,
"count": 80
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.402899532400004e-06,
"min": 1.402899532400004e-06,
"max": 0.0002383428205524,
"count": 80
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 5.611598129600016e-06,
"min": 5.611598129600016e-06,
"max": 0.001176864107712,
"count": 80
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.1004676,
"min": 0.1004676,
"max": 0.1794476,
"count": 80
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.4018704,
"min": 0.4018704,
"max": 0.892288,
"count": 80
},
"SnowballTarget.Policy.Beta.mean": {
"value": 3.3333240000000065e-05,
"min": 3.3333240000000065e-05,
"max": 0.00397443524,
"count": 80
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00013333296000000026,
"min": 0.00013333296000000026,
"max": 0.0196251712,
"count": 80
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 80
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 80
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 27.227272727272727,
"min": 25.522727272727273,
"max": 27.836363636363636,
"count": 80
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1198.0,
"min": 1123.0,
"max": 1531.0,
"count": 80
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 27.227272727272727,
"min": 25.522727272727273,
"max": 27.836363636363636,
"count": 80
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1198.0,
"min": 1123.0,
"max": 1531.0,
"count": 80
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 80
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 80
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1762943744",
"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 --resume --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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1762945467"
},
"total": 1722.771980468,
"count": 1,
"self": 0.4317561390000719,
"children": {
"run_training.setup": {
"total": 0.023216587999968397,
"count": 1,
"self": 0.023216587999968397
},
"TrainerController.start_learning": {
"total": 1722.317007741,
"count": 1,
"self": 1.343588427009763,
"children": {
"TrainerController._reset_env": {
"total": 2.2210760340001343,
"count": 1,
"self": 2.2210760340001343
},
"TrainerController.advance": {
"total": 1718.67612880799,
"count": 72728,
"self": 1.3913379469649954,
"children": {
"env_step": {
"total": 1245.530719770954,
"count": 72728,
"self": 975.5310014740139,
"children": {
"SubprocessEnvManager._take_step": {
"total": 269.1742891380211,
"count": 72728,
"self": 4.897090617062759,
"children": {
"TorchPolicy.evaluate": {
"total": 264.27719852095834,
"count": 72728,
"self": 264.27719852095834
}
}
},
"workers": {
"total": 0.8254291589189506,
"count": 72728,
"self": 0.0,
"children": {
"worker_root": {
"total": 1715.8887839449328,
"count": 72728,
"is_parallel": true,
"self": 856.8975963880007,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019576309998683428,
"count": 1,
"is_parallel": true,
"self": 0.0006123849996129138,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001345246000255429,
"count": 10,
"is_parallel": true,
"self": 0.001345246000255429
}
}
},
"UnityEnvironment.step": {
"total": 0.05622800499986624,
"count": 1,
"is_parallel": true,
"self": 0.000545989000102054,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00043507999998837477,
"count": 1,
"is_parallel": true,
"self": 0.00043507999998837477
},
"communicator.exchange": {
"total": 0.05341038799997477,
"count": 1,
"is_parallel": true,
"self": 0.05341038799997477
},
"steps_from_proto": {
"total": 0.0018365479998010414,
"count": 1,
"is_parallel": true,
"self": 0.00032387199939876155,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00151267600040228,
"count": 10,
"is_parallel": true,
"self": 0.00151267600040228
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 858.9911875569321,
"count": 72727,
"is_parallel": true,
"self": 40.91944866885524,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 21.938822124025137,
"count": 72727,
"is_parallel": true,
"self": 21.938822124025137
},
"communicator.exchange": {
"total": 652.3115750420532,
"count": 72727,
"is_parallel": true,
"self": 652.3115750420532
},
"steps_from_proto": {
"total": 143.82134172199858,
"count": 72727,
"is_parallel": true,
"self": 25.898806486143712,
"children": {
"_process_rank_one_or_two_observation": {
"total": 117.92253523585487,
"count": 727270,
"is_parallel": true,
"self": 117.92253523585487
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 471.75407109007097,
"count": 72728,
"self": 1.6955665870184475,
"children": {
"process_trajectory": {
"total": 104.97007734804924,
"count": 72728,
"self": 103.3971277860494,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5729495619998488,
"count": 16,
"self": 1.5729495619998488
}
}
},
"_update_policy": {
"total": 365.0884271550033,
"count": 363,
"self": 149.68199110103296,
"children": {
"TorchPPOOptimizer.update": {
"total": 215.4064360539703,
"count": 18510,
"self": 215.4064360539703
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0110002222063486e-06,
"count": 1,
"self": 1.0110002222063486e-06
},
"TrainerController._save_models": {
"total": 0.07621346099995208,
"count": 1,
"self": 0.0008707209999556653,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07534273999999641,
"count": 1,
"self": 0.07534273999999641
}
}
}
}
}
}
}