ppo-Huggy / run_logs /timers.json
tylerkiser's picture
Huggy
56f2f53
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4026554822921753,
"min": 1.4026554822921753,
"max": 1.4301259517669678,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71013.640625,
"min": 68208.609375,
"max": 77710.4921875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 98.0990099009901,
"min": 88.65036231884058,
"max": 389.3565891472868,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49540.0,
"min": 48719.0,
"max": 50227.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999988.0,
"min": 49873.0,
"max": 1999988.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999988.0,
"min": 49873.0,
"max": 1999988.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4543912410736084,
"min": 0.15265828371047974,
"max": 2.466923713684082,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1241.9219970703125,
"min": 19.540260314941406,
"max": 1349.5594482421875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8382084360235766,
"min": 1.796500314027071,
"max": 3.8558181784744185,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1942.1334686279297,
"min": 229.9520401954651,
"max": 2129.7079817056656,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8382084360235766,
"min": 1.796500314027071,
"max": 3.8558181784744185,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1942.1334686279297,
"min": 229.9520401954651,
"max": 2129.7079817056656,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015242608641953363,
"min": 0.013441422929948507,
"max": 0.02241278883842218,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.030485217283906726,
"min": 0.029275748034463804,
"max": 0.05757204872679722,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05686187924196323,
"min": 0.021645207361628612,
"max": 0.060205557569861415,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.11372375848392646,
"min": 0.043290414723257224,
"max": 0.17779117226600646,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.437398520899999e-06,
"min": 4.437398520899999e-06,
"max": 0.0002953656015448,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.874797041799999e-06,
"min": 8.874797041799999e-06,
"max": 0.0008438217187260998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10147909999999999,
"min": 0.10147909999999999,
"max": 0.19845520000000005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20295819999999998,
"min": 0.20295819999999998,
"max": 0.5812739,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.380709e-05,
"min": 8.380709e-05,
"max": 0.00492291448,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00016761418,
"min": 0.00016761418,
"max": 0.014065567610000001,
"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": "1695867300",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=Huggy --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1695869994"
},
"total": 2693.615451373,
"count": 1,
"self": 0.4375966050010902,
"children": {
"run_training.setup": {
"total": 0.04277871299927938,
"count": 1,
"self": 0.04277871299927938
},
"TrainerController.start_learning": {
"total": 2693.1350760549994,
"count": 1,
"self": 5.006926109741471,
"children": {
"TrainerController._reset_env": {
"total": 4.288722274000975,
"count": 1,
"self": 4.288722274000975
},
"TrainerController.advance": {
"total": 2683.7089476682577,
"count": 232182,
"self": 5.407964442310913,
"children": {
"env_step": {
"total": 2085.2201004999333,
"count": 232182,
"self": 1758.6513711027474,
"children": {
"SubprocessEnvManager._take_step": {
"total": 323.29176195321816,
"count": 232182,
"self": 18.093546065043483,
"children": {
"TorchPolicy.evaluate": {
"total": 305.1982158881747,
"count": 223048,
"self": 305.1982158881747
}
}
},
"workers": {
"total": 3.2769674439678056,
"count": 232182,
"self": 0.0,
"children": {
"worker_root": {
"total": 2685.014064523515,
"count": 232182,
"is_parallel": true,
"self": 1253.5775439712306,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0007606060007674387,
"count": 1,
"is_parallel": true,
"self": 0.0002469650025886949,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005136409981787438,
"count": 2,
"is_parallel": true,
"self": 0.0005136409981787438
}
}
},
"UnityEnvironment.step": {
"total": 0.03282290199967974,
"count": 1,
"is_parallel": true,
"self": 0.00032435600041935686,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00024283499988086987,
"count": 1,
"is_parallel": true,
"self": 0.00024283499988086987
},
"communicator.exchange": {
"total": 0.031445505999727175,
"count": 1,
"is_parallel": true,
"self": 0.031445505999727175
},
"steps_from_proto": {
"total": 0.0008102049996523419,
"count": 1,
"is_parallel": true,
"self": 0.0002452549979352625,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005649500017170794,
"count": 2,
"is_parallel": true,
"self": 0.0005649500017170794
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1431.4365205522845,
"count": 232181,
"is_parallel": true,
"self": 41.57818629153553,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 89.76971674773631,
"count": 232181,
"is_parallel": true,
"self": 89.76971674773631
},
"communicator.exchange": {
"total": 1195.4228326419288,
"count": 232181,
"is_parallel": true,
"self": 1195.4228326419288
},
"steps_from_proto": {
"total": 104.66578487108382,
"count": 232181,
"is_parallel": true,
"self": 39.913717689776604,
"children": {
"_process_rank_one_or_two_observation": {
"total": 64.75206718130721,
"count": 464362,
"is_parallel": true,
"self": 64.75206718130721
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 593.0808827260134,
"count": 232182,
"self": 7.197477306888686,
"children": {
"process_trajectory": {
"total": 154.51321417813597,
"count": 232182,
"self": 152.96361452913698,
"children": {
"RLTrainer._checkpoint": {
"total": 1.549599648998992,
"count": 10,
"self": 1.549599648998992
}
}
},
"_update_policy": {
"total": 431.3701912409888,
"count": 96,
"self": 368.8634118109203,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.50677943006849,
"count": 2880,
"self": 62.50677943006849
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2019991117995232e-06,
"count": 1,
"self": 1.2019991117995232e-06
},
"TrainerController._save_models": {
"total": 0.13047880100020848,
"count": 1,
"self": 0.0026741889996628743,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1278046120005456,
"count": 1,
"self": 0.1278046120005456
}
}
}
}
}
}
}