ppo-Hugggy / run_logs /timers.json
APRG's picture
Huggy
870b4cd verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.407529592514038,
"min": 1.407529592514038,
"max": 1.4279824495315552,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69909.1796875,
"min": 68628.4765625,
"max": 76627.2578125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 102.45773195876289,
"min": 88.90125673249551,
"max": 390.7890625,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49692.0,
"min": 48800.0,
"max": 50210.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999502.0,
"min": 49856.0,
"max": 1999502.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999502.0,
"min": 49856.0,
"max": 1999502.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4301843643188477,
"min": 0.10900904983282089,
"max": 2.442673683166504,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1178.639404296875,
"min": 13.844149589538574,
"max": 1319.59423828125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.804391896724701,
"min": 1.7949861426522413,
"max": 4.007215605469678,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1845.13006991148,
"min": 227.96324011683464,
"max": 2167.8920162916183,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.804391896724701,
"min": 1.7949861426522413,
"max": 4.007215605469678,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1845.13006991148,
"min": 227.96324011683464,
"max": 2167.8920162916183,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014935406622114693,
"min": 0.014744525553639202,
"max": 0.019541841893806124,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04480621986634408,
"min": 0.029489051107278404,
"max": 0.0560352119631716,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.051385036359230675,
"min": 0.022132812223086752,
"max": 0.05765120716144641,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15415510907769203,
"min": 0.044265624446173504,
"max": 0.16085108953217667,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.426748857783342e-06,
"min": 3.426748857783342e-06,
"max": 0.0002953342515552499,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0280246573350025e-05,
"min": 1.0280246573350025e-05,
"max": 0.0008440782186405998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10114221666666667,
"min": 0.10114221666666667,
"max": 0.19844474999999995,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30342665,
"min": 0.2074156,
"max": 0.5813594000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.699661166666681e-05,
"min": 6.699661166666681e-05,
"max": 0.004922393025,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020098983500000045,
"min": 0.00020098983500000045,
"max": 0.014069834059999996,
"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": "1767794113",
"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": "1767796654"
},
"total": 2541.380367482,
"count": 1,
"self": 0.4394778879996011,
"children": {
"run_training.setup": {
"total": 0.027114277999999103,
"count": 1,
"self": 0.027114277999999103
},
"TrainerController.start_learning": {
"total": 2540.9137753160003,
"count": 1,
"self": 4.089212395058894,
"children": {
"TrainerController._reset_env": {
"total": 2.7902888050000456,
"count": 1,
"self": 2.7902888050000456
},
"TrainerController.advance": {
"total": 2533.934126538941,
"count": 231773,
"self": 4.355682531631828,
"children": {
"env_step": {
"total": 2073.894880431133,
"count": 231773,
"self": 1669.0382473721845,
"children": {
"SubprocessEnvManager._take_step": {
"total": 402.25627490090665,
"count": 231773,
"self": 15.041782918961644,
"children": {
"TorchPolicy.evaluate": {
"total": 387.214491981945,
"count": 222956,
"self": 387.214491981945
}
}
},
"workers": {
"total": 2.6003581580418995,
"count": 231773,
"self": 0.0,
"children": {
"worker_root": {
"total": 2528.40291673492,
"count": 231773,
"is_parallel": true,
"self": 1175.6240674389992,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008534050000434945,
"count": 1,
"is_parallel": true,
"self": 0.0002553200001784717,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005980849998650228,
"count": 2,
"is_parallel": true,
"self": 0.0005980849998650228
}
}
},
"UnityEnvironment.step": {
"total": 0.04060531599998285,
"count": 1,
"is_parallel": true,
"self": 0.00034557100025267573,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019907599994439806,
"count": 1,
"is_parallel": true,
"self": 0.00019907599994439806
},
"communicator.exchange": {
"total": 0.039396904999875915,
"count": 1,
"is_parallel": true,
"self": 0.039396904999875915
},
"steps_from_proto": {
"total": 0.000663763999909861,
"count": 1,
"is_parallel": true,
"self": 0.00018750400022327085,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00047625999968659016,
"count": 2,
"is_parallel": true,
"self": 0.00047625999968659016
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1352.7788492959207,
"count": 231772,
"is_parallel": true,
"self": 38.351047460918835,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.2160826918373,
"count": 231772,
"is_parallel": true,
"self": 83.2160826918373
},
"communicator.exchange": {
"total": 1139.7511429140939,
"count": 231772,
"is_parallel": true,
"self": 1139.7511429140939
},
"steps_from_proto": {
"total": 91.46057622907074,
"count": 231772,
"is_parallel": true,
"self": 33.24811685907798,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.21245936999276,
"count": 463544,
"is_parallel": true,
"self": 58.21245936999276
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 455.6835635761763,
"count": 231773,
"self": 6.50853336615728,
"children": {
"process_trajectory": {
"total": 148.03163284302013,
"count": 231773,
"self": 146.8609955640204,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1706372789997204,
"count": 10,
"self": 1.1706372789997204
}
}
},
"_update_policy": {
"total": 301.1433973669989,
"count": 97,
"self": 239.36781951799708,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.77557784900182,
"count": 2910,
"self": 61.77557784900182
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0320000001229346e-06,
"count": 1,
"self": 1.0320000001229346e-06
},
"TrainerController._save_models": {
"total": 0.10014654499991593,
"count": 1,
"self": 0.0013282019999678596,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09881834299994807,
"count": 1,
"self": 0.09881834299994807
}
}
}
}
}
}
}