ppo-Huggy / run_logs /timers.json
FAYSSAL12's picture
Huggy
cf6f4d2 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4056042432785034,
"min": 1.4056042432785034,
"max": 1.4313067197799683,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 72454.6796875,
"min": 67989.984375,
"max": 78208.0,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 89.74410163339383,
"min": 81.05911330049261,
"max": 395.23622047244095,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49449.0,
"min": 49090.0,
"max": 50195.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999967.0,
"min": 49572.0,
"max": 1999967.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999967.0,
"min": 49572.0,
"max": 1999967.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.458632230758667,
"min": 0.16610635817050934,
"max": 2.4884634017944336,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1354.706298828125,
"min": 20.929401397705078,
"max": 1482.897216796875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7298209814324355,
"min": 1.85753637836093,
"max": 4.082558241949694,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2055.131360769272,
"min": 234.04958367347717,
"max": 2416.8744792342186,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7298209814324355,
"min": 1.85753637836093,
"max": 4.082558241949694,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2055.131360769272,
"min": 234.04958367347717,
"max": 2416.8744792342186,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01596530656493592,
"min": 0.013085865661075028,
"max": 0.019650566835593963,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04789591969480776,
"min": 0.026171731322150057,
"max": 0.05705685313308398,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.048946206354432635,
"min": 0.020353571170320113,
"max": 0.05819993598593606,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1468386190632979,
"min": 0.040707142340640226,
"max": 0.1745998079578082,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.735898754733333e-06,
"min": 3.735898754733333e-06,
"max": 0.00029536447654517496,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.12076962642e-05,
"min": 1.12076962642e-05,
"max": 0.00084395236868255,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10124526666666667,
"min": 0.10124526666666667,
"max": 0.19845482499999997,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3037358,
"min": 0.20769505,
"max": 0.58131745,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.213880666666668e-05,
"min": 7.213880666666668e-05,
"max": 0.004922895767500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021641642000000007,
"min": 0.00021641642000000007,
"max": 0.014067740755,
"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": "1714065028",
"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",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1714067473"
},
"total": 2444.6894440240003,
"count": 1,
"self": 0.7531073969994395,
"children": {
"run_training.setup": {
"total": 0.05336906800039287,
"count": 1,
"self": 0.05336906800039287
},
"TrainerController.start_learning": {
"total": 2443.8829675590005,
"count": 1,
"self": 4.399925078129854,
"children": {
"TrainerController._reset_env": {
"total": 2.867934403000163,
"count": 1,
"self": 2.867934403000163
},
"TrainerController.advance": {
"total": 2436.436440171871,
"count": 233039,
"self": 4.7563431025751015,
"children": {
"env_step": {
"total": 1950.7670054321206,
"count": 233039,
"self": 1619.8940835261992,
"children": {
"SubprocessEnvManager._take_step": {
"total": 327.89584539304497,
"count": 233039,
"self": 16.6847133219062,
"children": {
"TorchPolicy.evaluate": {
"total": 311.21113207113876,
"count": 223138,
"self": 311.21113207113876
}
}
},
"workers": {
"total": 2.977076512876465,
"count": 233039,
"self": 0.0,
"children": {
"worker_root": {
"total": 2436.3631060869243,
"count": 233039,
"is_parallel": true,
"self": 1130.109364957947,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009006990003399551,
"count": 1,
"is_parallel": true,
"self": 0.0002370380002503225,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006636610000896326,
"count": 2,
"is_parallel": true,
"self": 0.0006636610000896326
}
}
},
"UnityEnvironment.step": {
"total": 0.06438246600009734,
"count": 1,
"is_parallel": true,
"self": 0.00037131799990675063,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002013080002143397,
"count": 1,
"is_parallel": true,
"self": 0.0002013080002143397
},
"communicator.exchange": {
"total": 0.06292605899989212,
"count": 1,
"is_parallel": true,
"self": 0.06292605899989212
},
"steps_from_proto": {
"total": 0.0008837810000841273,
"count": 1,
"is_parallel": true,
"self": 0.0002175340000576398,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006662470000264875,
"count": 2,
"is_parallel": true,
"self": 0.0006662470000264875
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1306.2537411289773,
"count": 233038,
"is_parallel": true,
"self": 39.7797030388092,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 87.02347996810295,
"count": 233038,
"is_parallel": true,
"self": 87.02347996810295
},
"communicator.exchange": {
"total": 1085.767293651858,
"count": 233038,
"is_parallel": true,
"self": 1085.767293651858
},
"steps_from_proto": {
"total": 93.68326447020718,
"count": 233038,
"is_parallel": true,
"self": 35.70276507114613,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.980499399061046,
"count": 466076,
"is_parallel": true,
"self": 57.980499399061046
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 480.91309163717506,
"count": 233039,
"self": 6.56010423405678,
"children": {
"process_trajectory": {
"total": 162.6619951171233,
"count": 233039,
"self": 161.27130621112383,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3906889059994683,
"count": 10,
"self": 1.3906889059994683
}
}
},
"_update_policy": {
"total": 311.690992285995,
"count": 97,
"self": 251.01982931400835,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.67116297198663,
"count": 2910,
"self": 60.67116297198663
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4529996406054124e-06,
"count": 1,
"self": 1.4529996406054124e-06
},
"TrainerController._save_models": {
"total": 0.17866645300000528,
"count": 1,
"self": 0.0031221350000123493,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17554431799999293,
"count": 1,
"self": 0.17554431799999293
}
}
}
}
}
}
}