Haricot24601's picture
First Push
7dbb56f verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9018916487693787,
"min": 0.8959911465644836,
"max": 2.8254168033599854,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8571.578125,
"min": 8571.578125,
"max": 28841.85546875,
"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": 13.09937572479248,
"min": 0.14849677681922913,
"max": 13.09937572479248,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2554.378173828125,
"min": 28.808374404907227,
"max": 2632.91748046875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0620133121225152,
"min": 0.0620133121225152,
"max": 0.07341323921687481,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2480532484900608,
"min": 0.2480532484900608,
"max": 0.3670661960843741,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22095077441019167,
"min": 0.1238992186240377,
"max": 0.2941234820613674,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8838030976407667,
"min": 0.4955968744961508,
"max": 1.470617410306837,
"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": 25.65909090909091,
"min": 3.3863636363636362,
"max": 25.963636363636365,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1129.0,
"min": 149.0,
"max": 1428.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.65909090909091,
"min": 3.3863636363636362,
"max": 25.963636363636365,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1129.0,
"min": 149.0,
"max": 1428.0,
"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": "1743406184",
"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": "1743406655"
},
"total": 470.42889568500004,
"count": 1,
"self": 0.42750541699990663,
"children": {
"run_training.setup": {
"total": 0.023736943000017163,
"count": 1,
"self": 0.023736943000017163
},
"TrainerController.start_learning": {
"total": 469.9776533250001,
"count": 1,
"self": 0.38954281899498255,
"children": {
"TrainerController._reset_env": {
"total": 3.77891063200002,
"count": 1,
"self": 3.77891063200002
},
"TrainerController.advance": {
"total": 465.71697633500503,
"count": 18192,
"self": 0.38895552900476105,
"children": {
"env_step": {
"total": 332.54656092099697,
"count": 18192,
"self": 252.93250505499373,
"children": {
"SubprocessEnvManager._take_step": {
"total": 79.3933485950057,
"count": 18192,
"self": 1.430896846013752,
"children": {
"TorchPolicy.evaluate": {
"total": 77.96245174899195,
"count": 18192,
"self": 77.96245174899195
}
}
},
"workers": {
"total": 0.2207072709975364,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 468.2491708740098,
"count": 18192,
"is_parallel": true,
"self": 246.67702689301098,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008560068000065257,
"count": 1,
"is_parallel": true,
"self": 0.005806822000067768,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002753245999997489,
"count": 10,
"is_parallel": true,
"self": 0.002753245999997489
}
}
},
"UnityEnvironment.step": {
"total": 0.06328065900004276,
"count": 1,
"is_parallel": true,
"self": 0.0005716790000178662,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004172210000206178,
"count": 1,
"is_parallel": true,
"self": 0.0004172210000206178
},
"communicator.exchange": {
"total": 0.058973894000018845,
"count": 1,
"is_parallel": true,
"self": 0.058973894000018845
},
"steps_from_proto": {
"total": 0.0033178649999854315,
"count": 1,
"is_parallel": true,
"self": 0.0014841149996982494,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001833750000287182,
"count": 10,
"is_parallel": true,
"self": 0.001833750000287182
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 221.57214398099882,
"count": 18191,
"is_parallel": true,
"self": 10.313976183017985,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.845502517994987,
"count": 18191,
"is_parallel": true,
"self": 5.845502517994987
},
"communicator.exchange": {
"total": 171.05561579999596,
"count": 18191,
"is_parallel": true,
"self": 171.05561579999596
},
"steps_from_proto": {
"total": 34.35704947998988,
"count": 18191,
"is_parallel": true,
"self": 6.136945690023367,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.220103789966515,
"count": 181910,
"is_parallel": true,
"self": 28.220103789966515
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 132.7814598850033,
"count": 18192,
"self": 0.472265784005117,
"children": {
"process_trajectory": {
"total": 29.70693959199798,
"count": 18192,
"self": 29.134788310998033,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5721512809999467,
"count": 4,
"self": 0.5721512809999467
}
}
},
"_update_policy": {
"total": 102.6022545090002,
"count": 90,
"self": 42.02980703300352,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.57244747599668,
"count": 4587,
"self": 60.57244747599668
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.259999842470279e-07,
"count": 1,
"self": 9.259999842470279e-07
},
"TrainerController._save_models": {
"total": 0.09222261300010359,
"count": 1,
"self": 0.0010395369999969262,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09118307600010667,
"count": 1,
"self": 0.09118307600010667
}
}
}
}
}
}
}