S-Chaves's picture
First Push
74ded10 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9293270707130432,
"min": 0.9026452898979187,
"max": 2.855531930923462,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8832.32421875,
"min": 8832.32421875,
"max": 29149.26953125,
"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": 12.72242546081543,
"min": 0.3906298875808716,
"max": 12.72242546081543,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2480.873046875,
"min": 75.78219604492188,
"max": 2578.60595703125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07188019557318459,
"min": 0.06268985637796896,
"max": 0.07487869580126796,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28752078229273836,
"min": 0.27254534830446536,
"max": 0.37313883668123116,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1993418759575077,
"min": 0.1397856713121976,
"max": 0.2865734590034859,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7973675038300309,
"min": 0.5591426852487904,
"max": 1.4328672950174295,
"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.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.Environment.CumulativeReward.mean": {
"value": 25.227272727272727,
"min": 3.7954545454545454,
"max": 25.227272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1110.0,
"min": 167.0,
"max": 1375.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.227272727272727,
"min": 3.7954545454545454,
"max": 25.227272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1110.0,
"min": 167.0,
"max": 1375.0,
"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": "1744416625",
"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 --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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1744417053"
},
"total": 428.4539262950002,
"count": 1,
"self": 0.43726784500040594,
"children": {
"run_training.setup": {
"total": 0.02325796499962962,
"count": 1,
"self": 0.02325796499962962
},
"TrainerController.start_learning": {
"total": 427.99340048500017,
"count": 1,
"self": 0.3184410280609882,
"children": {
"TrainerController._reset_env": {
"total": 3.523773252999945,
"count": 1,
"self": 3.523773252999945
},
"TrainerController.advance": {
"total": 424.05775912293984,
"count": 18192,
"self": 0.35076169792455403,
"children": {
"env_step": {
"total": 299.15515515004427,
"count": 18192,
"self": 228.29988695001157,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.65983188101563,
"count": 18192,
"self": 1.224198256024465,
"children": {
"TorchPolicy.evaluate": {
"total": 69.43563362499117,
"count": 18192,
"self": 69.43563362499117
}
}
},
"workers": {
"total": 0.1954363190170625,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 426.6263427760023,
"count": 18192,
"is_parallel": true,
"self": 225.48785710599986,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006461144000240893,
"count": 1,
"is_parallel": true,
"self": 0.004192909001631051,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022682349986098416,
"count": 10,
"is_parallel": true,
"self": 0.0022682349986098416
}
}
},
"UnityEnvironment.step": {
"total": 0.06010326800014809,
"count": 1,
"is_parallel": true,
"self": 0.0006255300004340825,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003954229996452341,
"count": 1,
"is_parallel": true,
"self": 0.0003954229996452341
},
"communicator.exchange": {
"total": 0.056810450999819295,
"count": 1,
"is_parallel": true,
"self": 0.056810450999819295
},
"steps_from_proto": {
"total": 0.0022718640002494794,
"count": 1,
"is_parallel": true,
"self": 0.0003930489992853836,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018788150009640958,
"count": 10,
"is_parallel": true,
"self": 0.0018788150009640958
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 201.1384856700024,
"count": 18191,
"is_parallel": true,
"self": 9.886053055995035,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.272795384991696,
"count": 18191,
"is_parallel": true,
"self": 5.272795384991696
},
"communicator.exchange": {
"total": 154.9759133800253,
"count": 18191,
"is_parallel": true,
"self": 154.9759133800253
},
"steps_from_proto": {
"total": 31.003723848990376,
"count": 18191,
"is_parallel": true,
"self": 5.477196289129097,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.52652755986128,
"count": 181910,
"is_parallel": true,
"self": 25.52652755986128
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 124.55184227497102,
"count": 18192,
"self": 0.42099431899214323,
"children": {
"process_trajectory": {
"total": 26.646992741974827,
"count": 18192,
"self": 26.22032159897526,
"children": {
"RLTrainer._checkpoint": {
"total": 0.42667114299956665,
"count": 4,
"self": 0.42667114299956665
}
}
},
"_update_policy": {
"total": 97.48385521400405,
"count": 90,
"self": 38.895863154020844,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.58799205998321,
"count": 4587,
"self": 58.58799205998321
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1919996723008808e-06,
"count": 1,
"self": 1.1919996723008808e-06
},
"TrainerController._save_models": {
"total": 0.09342588899971815,
"count": 1,
"self": 0.0009116019996326941,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09251428700008546,
"count": 1,
"self": 0.09251428700008546
}
}
}
}
}
}
}