mihofer's picture
add cpu trained model
b65bbca verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9896315336227417,
"min": 0.9896315336227417,
"max": 2.8528997898101807,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9459.8876953125,
"min": 9459.8876953125,
"max": 29247.9296875,
"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": 12.357251167297363,
"min": 0.37132883071899414,
"max": 12.357251167297363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2409.6640625,
"min": 72.03779602050781,
"max": 2507.38232421875,
"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": 0.06993106799043244,
"min": 0.06310603887758072,
"max": 0.07426641959304392,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2797242719617298,
"min": 0.2554158271591672,
"max": 0.3713320979652196,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18121670730704187,
"min": 0.12521771460945041,
"max": 0.2607844745119413,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7248668292281675,
"min": 0.5008708584378017,
"max": 1.2650907039642334,
"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": 24.181818181818183,
"min": 3.4545454545454546,
"max": 24.327272727272728,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1064.0,
"min": 152.0,
"max": 1338.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.181818181818183,
"min": 3.4545454545454546,
"max": 24.327272727272728,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1064.0,
"min": 152.0,
"max": 1338.0,
"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": "1726385678",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.4.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1726386235"
},
"total": 556.754355864,
"count": 1,
"self": 0.48027847899993503,
"children": {
"run_training.setup": {
"total": 0.0682614560000161,
"count": 1,
"self": 0.0682614560000161
},
"TrainerController.start_learning": {
"total": 556.205815929,
"count": 1,
"self": 0.7835527100003219,
"children": {
"TrainerController._reset_env": {
"total": 2.495053753000036,
"count": 1,
"self": 2.495053753000036
},
"TrainerController.advance": {
"total": 552.8476913249997,
"count": 18202,
"self": 0.37227967000308126,
"children": {
"env_step": {
"total": 552.4754116549966,
"count": 18202,
"self": 425.19101095599984,
"children": {
"SubprocessEnvManager._take_step": {
"total": 126.88151584900106,
"count": 18202,
"self": 1.9271977009985335,
"children": {
"TorchPolicy.evaluate": {
"total": 124.95431814800253,
"count": 18202,
"self": 124.95431814800253
}
}
},
"workers": {
"total": 0.40288484999570073,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 554.6374535449987,
"count": 18202,
"is_parallel": true,
"self": 259.9462432460031,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002956929999982094,
"count": 1,
"is_parallel": true,
"self": 0.0011871419999351929,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017697880000469013,
"count": 10,
"is_parallel": true,
"self": 0.0017697880000469013
}
}
},
"UnityEnvironment.step": {
"total": 0.047019660999978896,
"count": 1,
"is_parallel": true,
"self": 0.0008886169999300364,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004644550000421077,
"count": 1,
"is_parallel": true,
"self": 0.0004644550000421077
},
"communicator.exchange": {
"total": 0.04331907700003512,
"count": 1,
"is_parallel": true,
"self": 0.04331907700003512
},
"steps_from_proto": {
"total": 0.00234751199997163,
"count": 1,
"is_parallel": true,
"self": 0.00045614499998691826,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018913669999847116,
"count": 10,
"is_parallel": true,
"self": 0.0018913669999847116
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 294.6912102989956,
"count": 18201,
"is_parallel": true,
"self": 13.567182594985468,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.845679997999923,
"count": 18201,
"is_parallel": true,
"self": 6.845679997999923
},
"communicator.exchange": {
"total": 231.9206796580046,
"count": 18201,
"is_parallel": true,
"self": 231.9206796580046
},
"steps_from_proto": {
"total": 42.35766804800562,
"count": 18201,
"is_parallel": true,
"self": 8.210653221992516,
"children": {
"_process_rank_one_or_two_observation": {
"total": 34.147014826013105,
"count": 182010,
"is_parallel": true,
"self": 34.147014826013105
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00016160999996372993,
"count": 1,
"self": 0.00016160999996372993,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 546.7318665929783,
"count": 733659,
"is_parallel": true,
"self": 16.17880626400597,
"children": {
"process_trajectory": {
"total": 295.5911926069725,
"count": 733659,
"is_parallel": true,
"self": 294.36676215497255,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2244304519999787,
"count": 4,
"is_parallel": true,
"self": 1.2244304519999787
}
}
},
"_update_policy": {
"total": 234.9618677219999,
"count": 90,
"is_parallel": true,
"self": 66.68770357400155,
"children": {
"TorchPPOOptimizer.update": {
"total": 168.27416414799836,
"count": 4587,
"is_parallel": true,
"self": 168.27416414799836
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.07935653099991669,
"count": 1,
"self": 0.001093837999974312,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07826269299994237,
"count": 1,
"self": 0.07826269299994237
}
}
}
}
}
}
}