ppo-Huggy / run_logs /timers.json
oukhan's picture
Huggy
743d495 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3981152772903442,
"min": 1.3981152772903442,
"max": 1.4266159534454346,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70504.15625,
"min": 68751.5390625,
"max": 76339.125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 72.32844574780059,
"min": 72.32844574780059,
"max": 423.74789915966386,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49328.0,
"min": 48863.0,
"max": 50426.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999988.0,
"min": 49907.0,
"max": 1999988.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999988.0,
"min": 49907.0,
"max": 1999988.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4609904289245605,
"min": 0.12524990737438202,
"max": 2.5549304485321045,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1678.3955078125,
"min": 14.779489517211914,
"max": 1678.3955078125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7676179518273147,
"min": 2.0322275846186333,
"max": 3.987300297714049,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2569.515443146229,
"min": 239.8028549849987,
"max": 2569.515443146229,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7676179518273147,
"min": 2.0322275846186333,
"max": 3.987300297714049,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2569.515443146229,
"min": 239.8028549849987,
"max": 2569.515443146229,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01818570559175896,
"min": 0.012071986283748021,
"max": 0.01938597735327979,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05455711677527688,
"min": 0.024143972567496043,
"max": 0.05455711677527688,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.056481432956126,
"min": 0.021763773324588936,
"max": 0.06263400930911303,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.169444298868378,
"min": 0.04352754664917787,
"max": 0.1837148230522871,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.7487987504333377e-06,
"min": 3.7487987504333377e-06,
"max": 0.00029529480156839996,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1246396251300014e-05,
"min": 1.1246396251300014e-05,
"max": 0.0008440059186646999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10124956666666667,
"min": 0.10124956666666667,
"max": 0.19843160000000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3037487,
"min": 0.20763575000000004,
"max": 0.5813353000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.235337666666675e-05,
"min": 7.235337666666675e-05,
"max": 0.004921736840000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021706013000000025,
"min": 0.00021706013000000025,
"max": 0.014068631470000002,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1769192784",
"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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1769197306"
},
"total": 4522.659842466001,
"count": 1,
"self": 0.7629522330007603,
"children": {
"run_training.setup": {
"total": 0.04923687200016502,
"count": 1,
"self": 0.04923687200016502
},
"TrainerController.start_learning": {
"total": 4521.847653361,
"count": 1,
"self": 8.007393125956696,
"children": {
"TrainerController._reset_env": {
"total": 4.336530733000018,
"count": 1,
"self": 4.336530733000018
},
"TrainerController.advance": {
"total": 4509.403094938044,
"count": 232982,
"self": 7.9324371410139065,
"children": {
"env_step": {
"total": 3047.4163535839507,
"count": 232982,
"self": 2593.0854033213013,
"children": {
"SubprocessEnvManager._take_step": {
"total": 449.26387692578146,
"count": 232982,
"self": 27.98458911285661,
"children": {
"TorchPolicy.evaluate": {
"total": 421.27928781292485,
"count": 222896,
"self": 421.27928781292485
}
}
},
"workers": {
"total": 5.067073336867907,
"count": 232982,
"self": 0.0,
"children": {
"worker_root": {
"total": 4499.804348080039,
"count": 232982,
"is_parallel": true,
"self": 2430.812449651803,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010607049998725415,
"count": 1,
"is_parallel": true,
"self": 0.00032781300023998483,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007328919996325567,
"count": 2,
"is_parallel": true,
"self": 0.0007328919996325567
}
}
},
"UnityEnvironment.step": {
"total": 0.04791267299970059,
"count": 1,
"is_parallel": true,
"self": 0.0005041509998591209,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00026807699987330125,
"count": 1,
"is_parallel": true,
"self": 0.00026807699987330125
},
"communicator.exchange": {
"total": 0.04592953800010946,
"count": 1,
"is_parallel": true,
"self": 0.04592953800010946
},
"steps_from_proto": {
"total": 0.0012109069998587074,
"count": 1,
"is_parallel": true,
"self": 0.0003888530000040191,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008220539998546883,
"count": 2,
"is_parallel": true,
"self": 0.0008220539998546883
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 2068.991898428236,
"count": 232981,
"is_parallel": true,
"self": 61.95518581848319,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 112.58477588979713,
"count": 232981,
"is_parallel": true,
"self": 112.58477588979713
},
"communicator.exchange": {
"total": 1758.2611721918643,
"count": 232981,
"is_parallel": true,
"self": 1758.2611721918643
},
"steps_from_proto": {
"total": 136.19076452809122,
"count": 232981,
"is_parallel": true,
"self": 43.84804447582337,
"children": {
"_process_rank_one_or_two_observation": {
"total": 92.34272005226785,
"count": 465962,
"is_parallel": true,
"self": 92.34272005226785
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1454.0543042130794,
"count": 232982,
"self": 11.82016671396832,
"children": {
"process_trajectory": {
"total": 236.57349035010884,
"count": 232982,
"self": 235.36426245410985,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2092278959989926,
"count": 10,
"self": 1.2092278959989926
}
}
},
"_update_policy": {
"total": 1205.6606471490022,
"count": 97,
"self": 315.01447983300204,
"children": {
"TorchPPOOptimizer.update": {
"total": 890.6461673160002,
"count": 2910,
"self": 890.6461673160002
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0619996828609146e-06,
"count": 1,
"self": 1.0619996828609146e-06
},
"TrainerController._save_models": {
"total": 0.1006335020001643,
"count": 1,
"self": 0.002488637000169547,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09814486499999475,
"count": 1,
"self": 0.09814486499999475
}
}
}
}
}
}
}