ppo-Huggy / run_logs /timers.json
Highsky7's picture
bonus unit1 exercise about Huggy(Highsky7)
99ceced verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4060211181640625,
"min": 1.4060211181640625,
"max": 1.4281928539276123,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70340.421875,
"min": 68844.109375,
"max": 77148.7890625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 84.57876712328768,
"min": 81.75249169435216,
"max": 399.232,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49394.0,
"min": 49215.0,
"max": 49904.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999991.0,
"min": 49709.0,
"max": 1999991.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999991.0,
"min": 49709.0,
"max": 1999991.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.417454481124878,
"min": 0.06348448991775513,
"max": 2.456411838531494,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1411.79345703125,
"min": 7.872076511383057,
"max": 1453.79736328125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6542063123763424,
"min": 1.8089426477109232,
"max": 3.8820895816502947,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2134.056486427784,
"min": 224.30888831615448,
"max": 2239.9931961894035,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6542063123763424,
"min": 1.8089426477109232,
"max": 3.8820895816502947,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2134.056486427784,
"min": 224.30888831615448,
"max": 2239.9931961894035,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017692049183986255,
"min": 0.013838555549429858,
"max": 0.01935079214745201,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05307614755195876,
"min": 0.02901946003961105,
"max": 0.05765773839555853,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05981887479623158,
"min": 0.023932027506331603,
"max": 0.06164559479802847,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17945662438869475,
"min": 0.047864055012663206,
"max": 0.17945662438869475,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4754488415499995e-06,
"min": 3.4754488415499995e-06,
"max": 0.00029532255155915,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0426346524649998e-05,
"min": 1.0426346524649998e-05,
"max": 0.0008440537686487499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10115845000000001,
"min": 0.10115845000000001,
"max": 0.19844085,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30347535000000003,
"min": 0.20746014999999995,
"max": 0.58135125,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.780665499999999e-05,
"min": 6.780665499999999e-05,
"max": 0.0049221984150000005,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020341996499999998,
"min": 0.00020341996499999998,
"max": 0.014069427374999997,
"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": "1740225695",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1740228189"
},
"total": 2494.400753541,
"count": 1,
"self": 0.44037459800028955,
"children": {
"run_training.setup": {
"total": 0.025300596999954905,
"count": 1,
"self": 0.025300596999954905
},
"TrainerController.start_learning": {
"total": 2493.935078346,
"count": 1,
"self": 4.382271634025983,
"children": {
"TrainerController._reset_env": {
"total": 3.313555776000044,
"count": 1,
"self": 3.313555776000044
},
"TrainerController.advance": {
"total": 2486.121430998974,
"count": 232299,
"self": 4.718127596936483,
"children": {
"env_step": {
"total": 2007.8213747111151,
"count": 232299,
"self": 1568.966297284111,
"children": {
"SubprocessEnvManager._take_step": {
"total": 436.0823425229904,
"count": 232299,
"self": 16.077025590000858,
"children": {
"TorchPolicy.evaluate": {
"total": 420.00531693298956,
"count": 222936,
"self": 420.00531693298956
}
}
},
"workers": {
"total": 2.772734904013646,
"count": 232299,
"self": 0.0,
"children": {
"worker_root": {
"total": 2486.559968062865,
"count": 232299,
"is_parallel": true,
"self": 1208.3159327909893,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010821909999094714,
"count": 1,
"is_parallel": true,
"self": 0.0002626089998329917,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008195820000764797,
"count": 2,
"is_parallel": true,
"self": 0.0008195820000764797
}
}
},
"UnityEnvironment.step": {
"total": 0.04536880900002416,
"count": 1,
"is_parallel": true,
"self": 0.0003176210000219726,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002070240000193735,
"count": 1,
"is_parallel": true,
"self": 0.0002070240000193735
},
"communicator.exchange": {
"total": 0.04416715299998941,
"count": 1,
"is_parallel": true,
"self": 0.04416715299998941
},
"steps_from_proto": {
"total": 0.0006770109999933993,
"count": 1,
"is_parallel": true,
"self": 0.00019289700003355392,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004841139999598454,
"count": 2,
"is_parallel": true,
"self": 0.0004841139999598454
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1278.2440352718759,
"count": 232298,
"is_parallel": true,
"self": 38.35665765277963,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.72352877107869,
"count": 232298,
"is_parallel": true,
"self": 84.72352877107869
},
"communicator.exchange": {
"total": 1065.0656114809929,
"count": 232298,
"is_parallel": true,
"self": 1065.0656114809929
},
"steps_from_proto": {
"total": 90.09823736702458,
"count": 232298,
"is_parallel": true,
"self": 33.68189130117446,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.41634606585012,
"count": 464596,
"is_parallel": true,
"self": 56.41634606585012
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 473.5819286909227,
"count": 232299,
"self": 6.6444774949212615,
"children": {
"process_trajectory": {
"total": 167.15732481000293,
"count": 232299,
"self": 165.73865349700384,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4186713129990949,
"count": 10,
"self": 1.4186713129990949
}
}
},
"_update_policy": {
"total": 299.7801263859985,
"count": 97,
"self": 236.11030027100264,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.669826114995885,
"count": 2910,
"self": 63.669826114995885
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.87999555945862e-07,
"count": 1,
"self": 9.87999555945862e-07
},
"TrainerController._save_models": {
"total": 0.11781894900013867,
"count": 1,
"self": 0.0020313250001890992,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11578762399994957,
"count": 1,
"self": 0.11578762399994957
}
}
}
}
}
}
}