dlarionov's picture
Test1
ac236d6 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9590464234352112,
"min": 0.9590464234352112,
"max": 2.8705782890319824,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9188.6240234375,
"min": 9188.6240234375,
"max": 29429.16796875,
"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": 12.555706977844238,
"min": 0.5007466077804565,
"max": 12.555706977844238,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2448.36279296875,
"min": 97.14483642578125,
"max": 2535.279296875,
"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": 0.0763053400179499,
"min": 0.06458245986111305,
"max": 0.0763053400179499,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3052213600717996,
"min": 0.26340656233472093,
"max": 0.36161566478974644,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19220659549475885,
"min": 0.10858442095637906,
"max": 0.2679292620397081,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7688263819790354,
"min": 0.43433768382551624,
"max": 1.3396463101985407,
"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.CumulativeReward.mean": {
"value": 24.772727272727273,
"min": 3.2954545454545454,
"max": 24.772727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1090.0,
"min": 145.0,
"max": 1357.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.772727272727273,
"min": 3.2954545454545454,
"max": 24.772727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1090.0,
"min": 145.0,
"max": 1357.0,
"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": "1721994141",
"python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=/content/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": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1721994762"
},
"total": 620.3749936429999,
"count": 1,
"self": 0.5830747809998229,
"children": {
"run_training.setup": {
"total": 0.07470798400004242,
"count": 1,
"self": 0.07470798400004242
},
"TrainerController.start_learning": {
"total": 619.7172108780001,
"count": 1,
"self": 0.8761192709960142,
"children": {
"TrainerController._reset_env": {
"total": 2.4522279709999566,
"count": 1,
"self": 2.4522279709999566
},
"TrainerController.advance": {
"total": 616.2853950650042,
"count": 18204,
"self": 0.43998901300437865,
"children": {
"env_step": {
"total": 615.8454060519998,
"count": 18204,
"self": 478.5058016869848,
"children": {
"SubprocessEnvManager._take_step": {
"total": 136.91467741500605,
"count": 18204,
"self": 2.608256036988223,
"children": {
"TorchPolicy.evaluate": {
"total": 134.30642137801783,
"count": 18204,
"self": 134.30642137801783
}
}
},
"workers": {
"total": 0.42492695000896674,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 617.5646796540025,
"count": 18204,
"is_parallel": true,
"self": 293.4062506969781,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0033894599998802732,
"count": 1,
"is_parallel": true,
"self": 0.001100421000046481,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022890389998337923,
"count": 10,
"is_parallel": true,
"self": 0.0022890389998337923
}
}
},
"UnityEnvironment.step": {
"total": 0.05707483599985608,
"count": 1,
"is_parallel": true,
"self": 0.0008799579998139961,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00046733299996049027,
"count": 1,
"is_parallel": true,
"self": 0.00046733299996049027
},
"communicator.exchange": {
"total": 0.053130751000026066,
"count": 1,
"is_parallel": true,
"self": 0.053130751000026066
},
"steps_from_proto": {
"total": 0.0025967940000555245,
"count": 1,
"is_parallel": true,
"self": 0.0004735620002520591,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021232319998034654,
"count": 10,
"is_parallel": true,
"self": 0.0021232319998034654
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 324.1584289570244,
"count": 18203,
"is_parallel": true,
"self": 15.540655701977357,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.874707383031364,
"count": 18203,
"is_parallel": true,
"self": 7.874707383031364
},
"communicator.exchange": {
"total": 255.2074099180088,
"count": 18203,
"is_parallel": true,
"self": 255.2074099180088
},
"steps_from_proto": {
"total": 45.53565595400687,
"count": 18203,
"is_parallel": true,
"self": 9.195211827023513,
"children": {
"_process_rank_one_or_two_observation": {
"total": 36.34044412698336,
"count": 182030,
"is_parallel": true,
"self": 36.34044412698336
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001871669999218284,
"count": 1,
"self": 0.0001871669999218284,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 609.3175831828587,
"count": 772936,
"is_parallel": true,
"self": 18.27690049584453,
"children": {
"process_trajectory": {
"total": 325.0775584980147,
"count": 772936,
"is_parallel": true,
"self": 323.7317298460148,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3458286519999092,
"count": 4,
"is_parallel": true,
"self": 1.3458286519999092
}
}
},
"_update_policy": {
"total": 265.9631241889995,
"count": 90,
"is_parallel": true,
"self": 74.06544429100063,
"children": {
"TorchPPOOptimizer.update": {
"total": 191.89767989799884,
"count": 4587,
"is_parallel": true,
"self": 191.89767989799884
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1032814039999721,
"count": 1,
"self": 0.0013313439999365073,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10195006000003559,
"count": 1,
"self": 0.10195006000003559
}
}
}
}
}
}
}