ppo-Huggy / run_logs /timers.json
iftekharCS's picture
Huggy
3027def verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.403214693069458,
"min": 1.403214693069458,
"max": 1.4285378456115723,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70775.34375,
"min": 24882.79296875,
"max": 72600.0234375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 89.4927536231884,
"min": 83.96428571428571,
"max": 362.08029197080293,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49400.0,
"min": 12261.0,
"max": 50238.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999939.0,
"min": 49918.0,
"max": 1999939.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999939.0,
"min": 49918.0,
"max": 1999939.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3794329166412354,
"min": 0.09575299918651581,
"max": 2.4521102905273438,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1313.447021484375,
"min": 3.2556018829345703,
"max": 1387.224609375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6555834399617235,
"min": 1.785131524590885,
"max": 4.033723282943601,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2017.8820588588715,
"min": 60.69447183609009,
"max": 2219.897513449192,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6555834399617235,
"min": 1.785131524590885,
"max": 4.033723282943601,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2017.8820588588715,
"min": 60.69447183609009,
"max": 2219.897513449192,
"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
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016697096722135835,
"min": 0.013116709681344218,
"max": 0.020147538315116738,
"count": 39
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05009129016640751,
"min": 0.026233419362688436,
"max": 0.05885764930183844,
"count": 39
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0486554893768496,
"min": 0.02425507285321752,
"max": 0.05870068131221665,
"count": 39
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1459664681305488,
"min": 0.04851014570643504,
"max": 0.17610204393664997,
"count": 39
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4659988447e-06,
"min": 3.4659988447e-06,
"max": 0.000289591878469375,
"count": 39
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.03979965341e-05,
"min": 1.03979965341e-05,
"max": 0.0008455527181490997,
"count": 39
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1011553,
"min": 0.1011553,
"max": 0.19653062500000007,
"count": 39
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3034659,
"min": 0.20752889999999996,
"max": 0.5818509000000001,
"count": 39
},
"Huggy.Policy.Beta.mean": {
"value": 6.764947e-05,
"min": 6.764947e-05,
"max": 0.004826878187500001,
"count": 39
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020294840999999998,
"min": 0.00020294840999999998,
"max": 0.01409435991,
"count": 39
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1716400656",
"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 --resume",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1716402979"
},
"total": 2322.9358541740003,
"count": 1,
"self": 0.4277476770002977,
"children": {
"run_training.setup": {
"total": 0.05224299499991503,
"count": 1,
"self": 0.05224299499991503
},
"TrainerController.start_learning": {
"total": 2322.4558635020003,
"count": 1,
"self": 4.226719199956733,
"children": {
"TrainerController._reset_env": {
"total": 2.2529467719998593,
"count": 1,
"self": 2.2529467719998593
},
"TrainerController.advance": {
"total": 2315.8536006630434,
"count": 227703,
"self": 4.5668286939348945,
"children": {
"env_step": {
"total": 1832.0647384420142,
"count": 227703,
"self": 1509.7230932871114,
"children": {
"SubprocessEnvManager._take_step": {
"total": 319.67853207506187,
"count": 227703,
"self": 15.665510663110808,
"children": {
"TorchPolicy.evaluate": {
"total": 304.01302141195106,
"count": 218724,
"self": 304.01302141195106
}
}
},
"workers": {
"total": 2.6631130798409686,
"count": 227703,
"self": 0.0,
"children": {
"worker_root": {
"total": 2315.6937912319595,
"count": 227703,
"is_parallel": true,
"self": 1102.7437776819459,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008254520000718912,
"count": 1,
"is_parallel": true,
"self": 0.00019453600020824524,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000630915999863646,
"count": 2,
"is_parallel": true,
"self": 0.000630915999863646
}
}
},
"UnityEnvironment.step": {
"total": 0.061437097999942125,
"count": 1,
"is_parallel": true,
"self": 0.00037967099979141494,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002049630002147751,
"count": 1,
"is_parallel": true,
"self": 0.0002049630002147751
},
"communicator.exchange": {
"total": 0.06017449000000852,
"count": 1,
"is_parallel": true,
"self": 0.06017449000000852
},
"steps_from_proto": {
"total": 0.000677973999927417,
"count": 1,
"is_parallel": true,
"self": 0.00016169499986062874,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005162790000667883,
"count": 2,
"is_parallel": true,
"self": 0.0005162790000667883
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1212.9500135500136,
"count": 227702,
"is_parallel": true,
"self": 37.93120674408533,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 77.96353308903895,
"count": 227702,
"is_parallel": true,
"self": 77.96353308903895
},
"communicator.exchange": {
"total": 1010.832024396987,
"count": 227702,
"is_parallel": true,
"self": 1010.832024396987
},
"steps_from_proto": {
"total": 86.22324931990238,
"count": 227702,
"is_parallel": true,
"self": 30.756778750048852,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.46647056985353,
"count": 455404,
"is_parallel": true,
"self": 55.46647056985353
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 479.22203352709425,
"count": 227703,
"self": 6.274309315107985,
"children": {
"process_trajectory": {
"total": 149.52656303198933,
"count": 227703,
"self": 148.08399940398908,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4425636280002436,
"count": 10,
"self": 1.4425636280002436
}
}
},
"_update_policy": {
"total": 323.42116117999694,
"count": 95,
"self": 261.04331599499596,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.37784518500098,
"count": 2850,
"self": 62.37784518500098
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.059999683813658e-07,
"count": 1,
"self": 9.059999683813658e-07
},
"TrainerController._save_models": {
"total": 0.1225959610001155,
"count": 1,
"self": 0.002637267999944015,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11995869300017148,
"count": 1,
"self": 0.11995869300017148
}
}
}
}
}
}
}