Isaacp's picture
First Training of SnowballTarget
6efb9af
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.091679334640503,
"min": 1.072754144668579,
"max": 2.8900864124298096,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10519.421875,
"min": 10266.2568359375,
"max": 29660.95703125,
"count": 50
},
"SnowballTarget.Step.mean": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Step.sum": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.40750789642334,
"min": 0.022577987983822823,
"max": 12.40750789642334,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2543.5390625,
"min": 4.380129814147949,
"max": 2543.5390625,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 24.654545454545456,
"min": 2.659090909090909,
"max": 24.954545454545453,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1356.0,
"min": 117.0,
"max": 1356.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.654545454545456,
"min": 2.659090909090909,
"max": 24.954545454545453,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1356.0,
"min": 117.0,
"max": 1356.0,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.032300519189448096,
"min": 0.025629080664657522,
"max": 0.0410877088822114,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.06460103837889619,
"min": 0.051258161329315044,
"max": 0.12025100523654449,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2396732869868477,
"min": 0.09886919024089971,
"max": 0.306469858934482,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.4793465739736954,
"min": 0.19773838048179943,
"max": 0.8858326387902102,
"count": 50
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.017698982400002e-06,
"min": 1.017698982400002e-06,
"max": 9.869760130240001e-05,
"count": 50
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 2.035397964800004e-06,
"min": 2.035397964800004e-06,
"max": 0.00027893282106720003,
"count": 50
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.1010176,
"min": 0.1010176,
"max": 0.19869760000000003,
"count": 50
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.2020352,
"min": 0.2020352,
"max": 0.5789328,
"count": 50
},
"SnowballTarget.Policy.Beta.mean": {
"value": 6.07782400000001e-05,
"min": 6.07782400000001e-05,
"max": 0.00493501024,
"count": 50
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0001215564800000002,
"min": 0.0001215564800000002,
"max": 0.01394874672,
"count": 50
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1676235610",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1676236463"
},
"total": 852.7494579730001,
"count": 1,
"self": 0.3236592030002612,
"children": {
"run_training.setup": {
"total": 0.10466184699998848,
"count": 1,
"self": 0.10466184699998848
},
"TrainerController.start_learning": {
"total": 852.3211369229998,
"count": 1,
"self": 1.0747234700029367,
"children": {
"TrainerController._reset_env": {
"total": 5.965534982000008,
"count": 1,
"self": 5.965534982000008
},
"TrainerController.advance": {
"total": 845.151020784997,
"count": 45478,
"self": 0.5661146029769952,
"children": {
"env_step": {
"total": 844.58490618202,
"count": 45478,
"self": 556.3271873130575,
"children": {
"SubprocessEnvManager._take_step": {
"total": 287.72515050496713,
"count": 45478,
"self": 3.275259801969696,
"children": {
"TorchPolicy.evaluate": {
"total": 284.44989070299744,
"count": 45478,
"self": 61.69718723907272,
"children": {
"TorchPolicy.sample_actions": {
"total": 222.75270346392472,
"count": 45478,
"self": 222.75270346392472
}
}
}
}
},
"workers": {
"total": 0.532568363995324,
"count": 45478,
"self": 0.0,
"children": {
"worker_root": {
"total": 850.4865523840467,
"count": 45478,
"is_parallel": true,
"self": 405.38811282101506,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005057656000190036,
"count": 1,
"is_parallel": true,
"self": 0.0036658120002357464,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013918439999542898,
"count": 10,
"is_parallel": true,
"self": 0.0013918439999542898
}
}
},
"UnityEnvironment.step": {
"total": 0.030816238000170415,
"count": 1,
"is_parallel": true,
"self": 0.0005266910002319491,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00025645799996709684,
"count": 1,
"is_parallel": true,
"self": 0.00025645799996709684
},
"communicator.exchange": {
"total": 0.028152893999958906,
"count": 1,
"is_parallel": true,
"self": 0.028152893999958906
},
"steps_from_proto": {
"total": 0.0018801950000124634,
"count": 1,
"is_parallel": true,
"self": 0.0004083769995304465,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001471818000482017,
"count": 10,
"is_parallel": true,
"self": 0.001471818000482017
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 445.09843956303166,
"count": 45477,
"is_parallel": true,
"self": 16.265260262006905,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.754117227982533,
"count": 45477,
"is_parallel": true,
"self": 8.754117227982533
},
"communicator.exchange": {
"total": 366.7771096640545,
"count": 45477,
"is_parallel": true,
"self": 366.7771096640545
},
"steps_from_proto": {
"total": 53.301952408987745,
"count": 45477,
"is_parallel": true,
"self": 11.54807864117356,
"children": {
"_process_rank_one_or_two_observation": {
"total": 41.753873767814184,
"count": 454770,
"is_parallel": true,
"self": 41.753873767814184
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001506069997958548,
"count": 1,
"self": 0.0001506069997958548,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 841.6515983816348,
"count": 736423,
"is_parallel": true,
"self": 11.479795078913867,
"children": {
"process_trajectory": {
"total": 606.8121904797222,
"count": 736423,
"is_parallel": true,
"self": 604.6215475507211,
"children": {
"RLTrainer._checkpoint": {
"total": 2.1906429290011147,
"count": 10,
"is_parallel": true,
"self": 2.1906429290011147
}
}
},
"_update_policy": {
"total": 223.35961282299877,
"count": 113,
"is_parallel": true,
"self": 97.80151828001499,
"children": {
"TorchPPOOptimizer.update": {
"total": 125.55809454298378,
"count": 2712,
"is_parallel": true,
"self": 125.55809454298378
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12970707900012712,
"count": 1,
"self": 0.0010865190001823066,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12862055999994482,
"count": 1,
"self": 0.12862055999994482
}
}
}
}
}
}
}