ppo-Huggy / run_logs /timers.json
LoreMoretti's picture
Huggy
74333c0 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4027025699615479,
"min": 1.4027025699615479,
"max": 1.425614356994629,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70142.140625,
"min": 67712.046875,
"max": 79170.046875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 96.51960784313725,
"min": 84.87628865979381,
"max": 396.37795275590554,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49225.0,
"min": 48834.0,
"max": 50340.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999614.0,
"min": 49717.0,
"max": 1999614.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999614.0,
"min": 49717.0,
"max": 1999614.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4240190982818604,
"min": 0.0758838802576065,
"max": 2.4777913093566895,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1236.249755859375,
"min": 9.561368942260742,
"max": 1418.7095947265625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7635493790402132,
"min": 1.7640864863282157,
"max": 3.9620680568640125,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1919.4101833105087,
"min": 222.2748972773552,
"max": 2286.4911140203476,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7635493790402132,
"min": 1.7640864863282157,
"max": 3.9620680568640125,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1919.4101833105087,
"min": 222.2748972773552,
"max": 2286.4911140203476,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015981562726018538,
"min": 0.015085359818961782,
"max": 0.020918760863908877,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04794468817805561,
"min": 0.030170719637923563,
"max": 0.05951224818466774,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05747999433014128,
"min": 0.02241281447932124,
"max": 0.06163745832939943,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17243998299042385,
"min": 0.04482562895864248,
"max": 0.17243998299042385,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.272598909166667e-06,
"min": 3.272598909166667e-06,
"max": 0.0002953746015418,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.8177967275e-06,
"min": 9.8177967275e-06,
"max": 0.0008440588686470499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10109083333333331,
"min": 0.10109083333333331,
"max": 0.19845820000000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30327249999999994,
"min": 0.20735040000000005,
"max": 0.5813529500000003,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.443258333333335e-05,
"min": 6.443258333333335e-05,
"max": 0.004923064179999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019329775000000006,
"min": 0.00019329775000000006,
"max": 0.014069512205,
"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": "1711702772",
"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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --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": "1711705054"
},
"total": 2281.79457275,
"count": 1,
"self": 0.43914825799993196,
"children": {
"run_training.setup": {
"total": 0.057197777000055794,
"count": 1,
"self": 0.057197777000055794
},
"TrainerController.start_learning": {
"total": 2281.298226715,
"count": 1,
"self": 4.11465968901075,
"children": {
"TrainerController._reset_env": {
"total": 3.3685336600000255,
"count": 1,
"self": 3.3685336600000255
},
"TrainerController.advance": {
"total": 2273.6935063219894,
"count": 232143,
"self": 4.33181236006385,
"children": {
"env_step": {
"total": 1807.9644235150013,
"count": 232143,
"self": 1496.6338302330278,
"children": {
"SubprocessEnvManager._take_step": {
"total": 308.7776952189114,
"count": 232143,
"self": 16.586439919945292,
"children": {
"TorchPolicy.evaluate": {
"total": 292.1912552989661,
"count": 223037,
"self": 292.1912552989661
}
}
},
"workers": {
"total": 2.5528980630621163,
"count": 232143,
"self": 0.0,
"children": {
"worker_root": {
"total": 2274.4367884799344,
"count": 232143,
"is_parallel": true,
"self": 1060.6716540578805,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001183608000019376,
"count": 1,
"is_parallel": true,
"self": 0.0002925679999634667,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008910400000559093,
"count": 2,
"is_parallel": true,
"self": 0.0008910400000559093
}
}
},
"UnityEnvironment.step": {
"total": 0.030599591999930453,
"count": 1,
"is_parallel": true,
"self": 0.00037209699996765266,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021745200001532794,
"count": 1,
"is_parallel": true,
"self": 0.00021745200001532794
},
"communicator.exchange": {
"total": 0.029264632999911555,
"count": 1,
"is_parallel": true,
"self": 0.029264632999911555
},
"steps_from_proto": {
"total": 0.0007454100000359176,
"count": 1,
"is_parallel": true,
"self": 0.0002028459999792176,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005425640000567,
"count": 2,
"is_parallel": true,
"self": 0.0005425640000567
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1213.765134422054,
"count": 232142,
"is_parallel": true,
"self": 37.8965224769895,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.26973367396795,
"count": 232142,
"is_parallel": true,
"self": 79.26973367396795
},
"communicator.exchange": {
"total": 1009.1180933671172,
"count": 232142,
"is_parallel": true,
"self": 1009.1180933671172
},
"steps_from_proto": {
"total": 87.48078490397938,
"count": 232142,
"is_parallel": true,
"self": 30.73570494011824,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.745079963861144,
"count": 464284,
"is_parallel": true,
"self": 56.745079963861144
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 461.39727044692415,
"count": 232143,
"self": 6.148615603896133,
"children": {
"process_trajectory": {
"total": 141.17271723702765,
"count": 232143,
"self": 139.89297413802683,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2797430990008252,
"count": 10,
"self": 1.2797430990008252
}
}
},
"_update_policy": {
"total": 314.07593760600037,
"count": 97,
"self": 252.39311793400634,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.682819671994025,
"count": 2910,
"self": 61.682819671994025
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2119999155402184e-06,
"count": 1,
"self": 1.2119999155402184e-06
},
"TrainerController._save_models": {
"total": 0.12152583199986111,
"count": 1,
"self": 0.001978560999759793,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11954727100010132,
"count": 1,
"self": 0.11954727100010132
}
}
}
}
}
}
}