{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.871087908744812,
"min": 0.871087908744812,
"max": 2.8625786304473877,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8336.3115234375,
"min": 8336.3115234375,
"max": 29378.64453125,
"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": 12.916280746459961,
"min": 0.3280637264251709,
"max": 12.916280746459961,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2518.6748046875,
"min": 63.64436340332031,
"max": 2619.173583984375,
"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": 0.07133679494697442,
"min": 0.05998353638621183,
"max": 0.07495188351729702,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2853471797878977,
"min": 0.23993414554484732,
"max": 0.36324963811321315,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22485743415560205,
"min": 0.15462924593456967,
"max": 0.281341386695995,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8994297366224082,
"min": 0.6185169837382787,
"max": 1.406706933479975,
"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": 25.272727272727273,
"min": 4.0,
"max": 25.527272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1112.0,
"min": 176.0,
"max": 1404.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.272727272727273,
"min": 4.0,
"max": 25.527272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1112.0,
"min": 176.0,
"max": 1404.0,
"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": "1732079164",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --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": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1732079773"
},
"total": 608.616539103,
"count": 1,
"self": 0.5417063920000373,
"children": {
"run_training.setup": {
"total": 0.1189814610000326,
"count": 1,
"self": 0.1189814610000326
},
"TrainerController.start_learning": {
"total": 607.95585125,
"count": 1,
"self": 0.861671162001926,
"children": {
"TrainerController._reset_env": {
"total": 6.265804818999982,
"count": 1,
"self": 6.265804818999982
},
"TrainerController.advance": {
"total": 600.738349901998,
"count": 18204,
"self": 0.43029835599213584,
"children": {
"env_step": {
"total": 600.3080515460059,
"count": 18204,
"self": 462.7031978899977,
"children": {
"SubprocessEnvManager._take_step": {
"total": 137.19215045500601,
"count": 18204,
"self": 2.4422448850069145,
"children": {
"TorchPolicy.evaluate": {
"total": 134.7499055699991,
"count": 18204,
"self": 134.7499055699991
}
}
},
"workers": {
"total": 0.41270320100221625,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 606.0820750499961,
"count": 18204,
"is_parallel": true,
"self": 290.6307890370026,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002703421999967759,
"count": 1,
"is_parallel": true,
"self": 0.0007818009999027709,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001921621000064988,
"count": 10,
"is_parallel": true,
"self": 0.001921621000064988
}
}
},
"UnityEnvironment.step": {
"total": 0.045218417000000954,
"count": 1,
"is_parallel": true,
"self": 0.0008414769999376404,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004558690000067145,
"count": 1,
"is_parallel": true,
"self": 0.0004558690000067145
},
"communicator.exchange": {
"total": 0.041004887000042345,
"count": 1,
"is_parallel": true,
"self": 0.041004887000042345
},
"steps_from_proto": {
"total": 0.0029161840000142547,
"count": 1,
"is_parallel": true,
"self": 0.0004804569999805608,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002435727000033694,
"count": 10,
"is_parallel": true,
"self": 0.002435727000033694
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 315.4512860129935,
"count": 18203,
"is_parallel": true,
"self": 15.125661574979802,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.594395937006595,
"count": 18203,
"is_parallel": true,
"self": 7.594395937006595
},
"communicator.exchange": {
"total": 248.03754275100283,
"count": 18203,
"is_parallel": true,
"self": 248.03754275100283
},
"steps_from_proto": {
"total": 44.69368575000425,
"count": 18203,
"is_parallel": true,
"self": 9.078300663994298,
"children": {
"_process_rank_one_or_two_observation": {
"total": 35.61538508600995,
"count": 182030,
"is_parallel": true,
"self": 35.61538508600995
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00020545699999274802,
"count": 1,
"self": 0.00020545699999274802,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 593.8170439430022,
"count": 773102,
"is_parallel": true,
"self": 17.81109672708976,
"children": {
"process_trajectory": {
"total": 315.40278315191205,
"count": 773102,
"is_parallel": true,
"self": 314.4101245229121,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9926586289999477,
"count": 4,
"is_parallel": true,
"self": 0.9926586289999477
}
}
},
"_update_policy": {
"total": 260.6031640640004,
"count": 90,
"is_parallel": true,
"self": 72.6587098480041,
"children": {
"TorchPPOOptimizer.update": {
"total": 187.9444542159963,
"count": 4584,
"is_parallel": true,
"self": 187.9444542159963
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08981991000007383,
"count": 1,
"self": 0.0013650430000780034,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08845486699999583,
"count": 1,
"self": 0.08845486699999583
}
}
}
}
}
}
}