ppo-Huggy / run_logs /timers.json
liaohongyue's picture
Huggy
663aebe verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4012690782546997,
"min": 1.401267647743225,
"max": 1.4286872148513794,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68793.90625,
"min": 67767.171875,
"max": 77141.3125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 76.23647604327667,
"min": 74.09118541033435,
"max": 398.3968253968254,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49325.0,
"min": 48752.0,
"max": 50198.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999977.0,
"min": 49857.0,
"max": 1999977.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999977.0,
"min": 49857.0,
"max": 1999977.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4052183628082275,
"min": 0.15130232274532318,
"max": 2.491246461868286,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1556.17626953125,
"min": 18.912790298461914,
"max": 1600.190673828125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7732608103678436,
"min": 2.003600422382355,
"max": 4.059772270155872,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2441.299744307995,
"min": 250.45005279779434,
"max": 2522.3547630906105,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7732608103678436,
"min": 2.003600422382355,
"max": 4.059772270155872,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2441.299744307995,
"min": 250.45005279779434,
"max": 2522.3547630906105,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016905181196893358,
"min": 0.013195080979009313,
"max": 0.019118183942434065,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.050715543590680076,
"min": 0.026390161958018625,
"max": 0.0565261464957075,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.058149211977918946,
"min": 0.022511929180473088,
"max": 0.06460551482935747,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17444763593375684,
"min": 0.045023858360946176,
"max": 0.1908343467861414,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.7555487481833383e-06,
"min": 3.7555487481833383e-06,
"max": 0.00029535375154875003,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1266646244550015e-05,
"min": 1.1266646244550015e-05,
"max": 0.0008440836186387999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10125181666666666,
"min": 0.10125181666666666,
"max": 0.19845124999999997,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30375545,
"min": 0.20762930000000007,
"max": 0.5813612,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.246565166666673e-05,
"min": 7.246565166666673e-05,
"max": 0.004922717375000002,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002173969550000002,
"min": 0.0002173969550000002,
"max": 0.014069923880000001,
"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": "1740021308",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/home/alien/.local/share/mamba/envs/deep-rl/bin/mlagents-learn ./config/ppo/Huggy.yaml --force --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": "1740022666"
},
"total": 1357.7964134029999,
"count": 1,
"self": 0.2178866129988819,
"children": {
"run_training.setup": {
"total": 0.017069440000341274,
"count": 1,
"self": 0.017069440000341274
},
"TrainerController.start_learning": {
"total": 1357.5614573500006,
"count": 1,
"self": 2.874462373717506,
"children": {
"TrainerController._reset_env": {
"total": 1.4025550460000886,
"count": 1,
"self": 1.4025550460000886
},
"TrainerController.advance": {
"total": 1353.212950256282,
"count": 233018,
"self": 2.9863546080059677,
"children": {
"env_step": {
"total": 1067.1052491540158,
"count": 233018,
"self": 765.7059632239971,
"children": {
"SubprocessEnvManager._take_step": {
"total": 299.3680459078578,
"count": 233018,
"self": 8.832734115799212,
"children": {
"TorchPolicy.evaluate": {
"total": 290.53531179205856,
"count": 222916,
"self": 290.53531179205856
}
}
},
"workers": {
"total": 2.0312400221610005,
"count": 233018,
"self": 0.0,
"children": {
"worker_root": {
"total": 1353.9775844667947,
"count": 233018,
"is_parallel": true,
"self": 754.830675590978,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00037900900042586727,
"count": 1,
"is_parallel": true,
"self": 0.00011263500073255273,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00026637399969331454,
"count": 2,
"is_parallel": true,
"self": 0.00026637399969331454
}
}
},
"UnityEnvironment.step": {
"total": 0.012613253000381519,
"count": 1,
"is_parallel": true,
"self": 9.799100007512607e-05,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.480599990434712e-05,
"count": 1,
"is_parallel": true,
"self": 8.480599990434712e-05
},
"communicator.exchange": {
"total": 0.012193196999760403,
"count": 1,
"is_parallel": true,
"self": 0.012193196999760403
},
"steps_from_proto": {
"total": 0.00023725900064164307,
"count": 1,
"is_parallel": true,
"self": 7.24240007912158e-05,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00016483499985042727,
"count": 2,
"is_parallel": true,
"self": 0.00016483499985042727
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 599.1469088758167,
"count": 233017,
"is_parallel": true,
"self": 23.704592710669203,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 43.16010732317045,
"count": 233017,
"is_parallel": true,
"self": 43.16010732317045
},
"communicator.exchange": {
"total": 478.5417131502618,
"count": 233017,
"is_parallel": true,
"self": 478.5417131502618
},
"steps_from_proto": {
"total": 53.740495691715296,
"count": 233017,
"is_parallel": true,
"self": 18.023252465097357,
"children": {
"_process_rank_one_or_two_observation": {
"total": 35.71724322661794,
"count": 466034,
"is_parallel": true,
"self": 35.71724322661794
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 283.12134649426025,
"count": 233018,
"self": 3.8242349822357937,
"children": {
"process_trajectory": {
"total": 119.92096976003086,
"count": 233018,
"self": 119.01642540302964,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9045443570012139,
"count": 10,
"self": 0.9045443570012139
}
}
},
"_update_policy": {
"total": 159.3761417519936,
"count": 97,
"self": 128.10620576700694,
"children": {
"TorchPPOOptimizer.update": {
"total": 31.26993598498666,
"count": 2910,
"self": 31.26993598498666
}
}
}
}
}
}
},
"trainer_threads": {
"total": 5.990004865452647e-07,
"count": 1,
"self": 5.990004865452647e-07
},
"TrainerController._save_models": {
"total": 0.07148907500049972,
"count": 1,
"self": 0.0013695030011149356,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07011957199938479,
"count": 1,
"self": 0.07011957199938479
}
}
}
}
}
}
}