milotix's picture
First Push
cb80ca3 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8922310471534729,
"min": 0.8922310471534729,
"max": 2.870310068130493,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8548.4658203125,
"min": 8548.4658203125,
"max": 29426.41796875,
"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": 12.980125427246094,
"min": 0.5095755457878113,
"max": 12.980125427246094,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2531.12451171875,
"min": 98.85765075683594,
"max": 2638.2919921875,
"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": 0.06425605390227158,
"min": 0.06345996110798224,
"max": 0.07967915578125279,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25702421560908634,
"min": 0.25702421560908634,
"max": 0.35368544504893307,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21135788038372993,
"min": 0.11942218381377376,
"max": 0.30548540523239215,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8454315215349197,
"min": 0.47768873525509503,
"max": 1.5274270261619607,
"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.CumulativeReward.mean": {
"value": 25.613636363636363,
"min": 3.522727272727273,
"max": 25.727272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1127.0,
"min": 155.0,
"max": 1385.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.613636363636363,
"min": 3.522727272727273,
"max": 25.727272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1127.0,
"min": 155.0,
"max": 1385.0,
"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": "1710775905",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1710776520"
},
"total": 614.4504050110008,
"count": 1,
"self": 0.5901064850004332,
"children": {
"run_training.setup": {
"total": 0.07552316700002848,
"count": 1,
"self": 0.07552316700002848
},
"TrainerController.start_learning": {
"total": 613.7847753590004,
"count": 1,
"self": 0.894970867045231,
"children": {
"TrainerController._reset_env": {
"total": 4.905348344999766,
"count": 1,
"self": 4.905348344999766
},
"TrainerController.advance": {
"total": 607.8638753659552,
"count": 18202,
"self": 0.47529635901355505,
"children": {
"env_step": {
"total": 607.3885790069417,
"count": 18202,
"self": 462.90678934209063,
"children": {
"SubprocessEnvManager._take_step": {
"total": 144.04714124796737,
"count": 18202,
"self": 2.7966829906699786,
"children": {
"TorchPolicy.evaluate": {
"total": 141.2504582572974,
"count": 18202,
"self": 141.2504582572974
}
}
},
"workers": {
"total": 0.43464841688364686,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 611.6466390301139,
"count": 18202,
"is_parallel": true,
"self": 287.88524658824736,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008846821000588534,
"count": 1,
"is_parallel": true,
"self": 0.0065666450009302935,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022801759996582405,
"count": 10,
"is_parallel": true,
"self": 0.0022801759996582405
}
}
},
"UnityEnvironment.step": {
"total": 0.07372661999943375,
"count": 1,
"is_parallel": true,
"self": 0.0009155129991995636,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004897740000160411,
"count": 1,
"is_parallel": true,
"self": 0.0004897740000160411
},
"communicator.exchange": {
"total": 0.0653550870001709,
"count": 1,
"is_parallel": true,
"self": 0.0653550870001709
},
"steps_from_proto": {
"total": 0.006966246000047249,
"count": 1,
"is_parallel": true,
"self": 0.0040769989991531475,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002889247000894102,
"count": 10,
"is_parallel": true,
"self": 0.002889247000894102
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 323.7613924418665,
"count": 18201,
"is_parallel": true,
"self": 15.926791577943732,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.76903621292513,
"count": 18201,
"is_parallel": true,
"self": 7.76903621292513
},
"communicator.exchange": {
"total": 253.47262861492982,
"count": 18201,
"is_parallel": true,
"self": 253.47262861492982
},
"steps_from_proto": {
"total": 46.59293603606784,
"count": 18201,
"is_parallel": true,
"self": 9.354955408804926,
"children": {
"_process_rank_one_or_two_observation": {
"total": 37.237980627262914,
"count": 182010,
"is_parallel": true,
"self": 37.237980627262914
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0002379810011916561,
"count": 1,
"self": 0.0002379810011916561,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 600.0858544236662,
"count": 820671,
"is_parallel": true,
"self": 20.077477235436163,
"children": {
"process_trajectory": {
"total": 327.4971394512304,
"count": 820671,
"is_parallel": true,
"self": 326.61557667523084,
"children": {
"RLTrainer._checkpoint": {
"total": 0.881562775999555,
"count": 4,
"is_parallel": true,
"self": 0.881562775999555
}
}
},
"_update_policy": {
"total": 252.51123773699965,
"count": 90,
"is_parallel": true,
"self": 64.27807264202056,
"children": {
"TorchPPOOptimizer.update": {
"total": 188.23316509497909,
"count": 4587,
"is_parallel": true,
"self": 188.23316509497909
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1203427999989799,
"count": 1,
"self": 0.0014329129990073852,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11890988699997251,
"count": 1,
"self": 0.11890988699997251
}
}
}
}
}
}
}