AIventurer's picture
First Push
573490f verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9119991064071655,
"min": 0.9119991064071655,
"max": 2.855494499206543,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8667.6396484375,
"min": 8667.6396484375,
"max": 29148.888671875,
"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": 12.961627006530762,
"min": 0.5080426931381226,
"max": 12.961627006530762,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2527.517333984375,
"min": 98.56028747558594,
"max": 2626.3564453125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07404259061078454,
"min": 0.06422066711512146,
"max": 0.0764992126362403,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.29617036244313816,
"min": 0.25688266846048585,
"max": 0.36553311622792894,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20819605397535307,
"min": 0.12113643169298074,
"max": 0.2932913713887626,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8327842159014123,
"min": 0.484545726771923,
"max": 1.3467890786774017,
"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": 25.545454545454547,
"min": 3.9545454545454546,
"max": 25.672727272727272,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1124.0,
"min": 174.0,
"max": 1412.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.545454545454547,
"min": 3.9545454545454546,
"max": 25.672727272727272,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1124.0,
"min": 174.0,
"max": 1412.0,
"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": "1740102308",
"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=SnowballTarget3 --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": "1740102747"
},
"total": 438.36268291199985,
"count": 1,
"self": 0.4390935889998673,
"children": {
"run_training.setup": {
"total": 0.022391084999981103,
"count": 1,
"self": 0.022391084999981103
},
"TrainerController.start_learning": {
"total": 437.901198238,
"count": 1,
"self": 0.39516855999670497,
"children": {
"TrainerController._reset_env": {
"total": 2.8545923679999987,
"count": 1,
"self": 2.8545923679999987
},
"TrainerController.advance": {
"total": 434.5178873080031,
"count": 18192,
"self": 0.3793345660091063,
"children": {
"env_step": {
"total": 309.9834132970067,
"count": 18192,
"self": 234.7167190760049,
"children": {
"SubprocessEnvManager._take_step": {
"total": 75.04166435800323,
"count": 18192,
"self": 1.314941453988581,
"children": {
"TorchPolicy.evaluate": {
"total": 73.72672290401465,
"count": 18192,
"self": 73.72672290401465
}
}
},
"workers": {
"total": 0.22502986299855365,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 436.18245261400864,
"count": 18192,
"is_parallel": true,
"self": 230.82428381899706,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005485442999997758,
"count": 1,
"is_parallel": true,
"self": 0.003987746000007064,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014976969999906942,
"count": 10,
"is_parallel": true,
"self": 0.0014976969999906942
}
}
},
"UnityEnvironment.step": {
"total": 0.03780334199996105,
"count": 1,
"is_parallel": true,
"self": 0.0006113099999538463,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041723900005763426,
"count": 1,
"is_parallel": true,
"self": 0.00041723900005763426
},
"communicator.exchange": {
"total": 0.03481992899992292,
"count": 1,
"is_parallel": true,
"self": 0.03481992899992292
},
"steps_from_proto": {
"total": 0.001954864000026646,
"count": 1,
"is_parallel": true,
"self": 0.00035567199995512055,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015991920000715254,
"count": 10,
"is_parallel": true,
"self": 0.0015991920000715254
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 205.35816879501158,
"count": 18191,
"is_parallel": true,
"self": 9.888952545021311,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.466419156004008,
"count": 18191,
"is_parallel": true,
"self": 5.466419156004008
},
"communicator.exchange": {
"total": 157.9432606319964,
"count": 18191,
"is_parallel": true,
"self": 157.9432606319964
},
"steps_from_proto": {
"total": 32.059536461989865,
"count": 18191,
"is_parallel": true,
"self": 5.777348707009764,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.2821877549801,
"count": 181910,
"is_parallel": true,
"self": 26.2821877549801
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 124.1551394449873,
"count": 18192,
"self": 0.49313090697091866,
"children": {
"process_trajectory": {
"total": 27.185725755015596,
"count": 18192,
"self": 26.59716337701559,
"children": {
"RLTrainer._checkpoint": {
"total": 0.588562378000006,
"count": 4,
"self": 0.588562378000006
}
}
},
"_update_policy": {
"total": 96.47628278300078,
"count": 90,
"self": 38.01989659900096,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.456386183999825,
"count": 4587,
"self": 58.456386183999825
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4290001217887038e-06,
"count": 1,
"self": 1.4290001217887038e-06
},
"TrainerController._save_models": {
"total": 0.13354857300009826,
"count": 1,
"self": 0.0013328200000159995,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13221575300008226,
"count": 1,
"self": 0.13221575300008226
}
}
}
}
}
}
}