kporzycki's picture
First Push
5dec4e4
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0629292726516724,
"min": 1.0629292726516724,
"max": 2.8687009811401367,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10160.541015625,
"min": 10160.541015625,
"max": 29378.3671875,
"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": 11.539353370666504,
"min": 0.378068208694458,
"max": 11.539353370666504,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2250.173828125,
"min": 73.34523010253906,
"max": 2306.478759765625,
"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": 0.07802590237299549,
"min": 0.06662272802795462,
"max": 0.07872219718118169,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.31210360949198196,
"min": 0.2762940401820849,
"max": 0.36106370492637446,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20481962630269573,
"min": 0.12635378676521428,
"max": 0.2644697220302096,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8192785052107829,
"min": 0.5054151470608571,
"max": 1.3223486101510478,
"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": 0.0002252506000000002,
"min": 0.0002252506000000002,
"max": 0.0077837906,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0009010024000000008,
"min": 0.0009010024000000008,
"max": 0.036941428000000005,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 23.136363636363637,
"min": 3.3863636363636362,
"max": 23.136363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1018.0,
"min": 149.0,
"max": 1246.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.136363636363637,
"min": 3.3863636363636362,
"max": 23.136363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1018.0,
"min": 149.0,
"max": 1246.0,
"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": "1696880315",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.0.1+cu118",
"numpy_version": "1.21.2",
"end_time_seconds": "1696880841"
},
"total": 525.2646029800001,
"count": 1,
"self": 0.7451478989999032,
"children": {
"run_training.setup": {
"total": 0.046326092000072094,
"count": 1,
"self": 0.046326092000072094
},
"TrainerController.start_learning": {
"total": 524.4731289890001,
"count": 1,
"self": 0.6280367960009698,
"children": {
"TrainerController._reset_env": {
"total": 7.580063938999956,
"count": 1,
"self": 7.580063938999956
},
"TrainerController.advance": {
"total": 516.1191957449989,
"count": 18202,
"self": 0.29863043600244055,
"children": {
"env_step": {
"total": 515.8205653089965,
"count": 18202,
"self": 352.38076916001023,
"children": {
"SubprocessEnvManager._take_step": {
"total": 163.12521977798133,
"count": 18202,
"self": 1.6056480579718482,
"children": {
"TorchPolicy.evaluate": {
"total": 161.51957172000948,
"count": 18202,
"self": 161.51957172000948
}
}
},
"workers": {
"total": 0.3145763710049323,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 523.0226538999832,
"count": 18202,
"is_parallel": true,
"self": 255.61319478298742,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0023237140001128864,
"count": 1,
"is_parallel": true,
"self": 0.000675303999969401,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016484100001434854,
"count": 10,
"is_parallel": true,
"self": 0.0016484100001434854
}
}
},
"UnityEnvironment.step": {
"total": 0.08953024599986747,
"count": 1,
"is_parallel": true,
"self": 0.0006767499999114079,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00046696999993400823,
"count": 1,
"is_parallel": true,
"self": 0.00046696999993400823
},
"communicator.exchange": {
"total": 0.08605518299987125,
"count": 1,
"is_parallel": true,
"self": 0.08605518299987125
},
"steps_from_proto": {
"total": 0.0023313430001508095,
"count": 1,
"is_parallel": true,
"self": 0.0004881540003225382,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018431889998282713,
"count": 10,
"is_parallel": true,
"self": 0.0018431889998282713
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 267.4094591169958,
"count": 18201,
"is_parallel": true,
"self": 11.430042477993084,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.980520098992656,
"count": 18201,
"is_parallel": true,
"self": 5.980520098992656
},
"communicator.exchange": {
"total": 207.81570899100439,
"count": 18201,
"is_parallel": true,
"self": 207.81570899100439
},
"steps_from_proto": {
"total": 42.18318754900565,
"count": 18201,
"is_parallel": true,
"self": 7.811966569009655,
"children": {
"_process_rank_one_or_two_observation": {
"total": 34.371220979996,
"count": 182010,
"is_parallel": true,
"self": 34.371220979996
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001463250000597327,
"count": 1,
"self": 0.0001463250000597327,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 511.13764984705585,
"count": 534785,
"is_parallel": true,
"self": 12.047306073078971,
"children": {
"process_trajectory": {
"total": 284.32389839997654,
"count": 534785,
"is_parallel": true,
"self": 283.6187739809766,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7051244189999579,
"count": 4,
"is_parallel": true,
"self": 0.7051244189999579
}
}
},
"_update_policy": {
"total": 214.76644537400034,
"count": 90,
"is_parallel": true,
"self": 78.3501368830016,
"children": {
"TorchPPOOptimizer.update": {
"total": 136.41630849099874,
"count": 4587,
"is_parallel": true,
"self": 136.41630849099874
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1456861840001693,
"count": 1,
"self": 0.0012133689999700437,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14447281500019926,
"count": 1,
"self": 0.14447281500019926
}
}
}
}
}
}
}