ppo-Huggy / run_logs /timers.json
Liogl's picture
Huggy
52342a3
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4073128700256348,
"min": 1.4073128700256348,
"max": 1.4297382831573486,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69697.171875,
"min": 67705.453125,
"max": 77574.3671875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 99.6633064516129,
"min": 86.99290780141844,
"max": 412.56198347107437,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49433.0,
"min": 49064.0,
"max": 50162.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999956.0,
"min": 49642.0,
"max": 1999956.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999956.0,
"min": 49642.0,
"max": 1999956.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.319512128829956,
"min": 0.05916117504239082,
"max": 2.4685821533203125,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1150.47802734375,
"min": 7.099340915679932,
"max": 1342.2540283203125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6447724410362783,
"min": 1.7579586004217467,
"max": 3.963152125703566,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1807.807130753994,
"min": 210.9550320506096,
"max": 2197.5071779489517,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6447724410362783,
"min": 1.7579586004217467,
"max": 3.963152125703566,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1807.807130753994,
"min": 210.9550320506096,
"max": 2197.5071779489517,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018294125858422678,
"min": 0.013527012545819162,
"max": 0.01929765784977159,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05488237757526804,
"min": 0.027054025091638324,
"max": 0.057113949246680326,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04647088936633534,
"min": 0.021102071553468705,
"max": 0.06761536055968868,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.13941266809900602,
"min": 0.04220414310693741,
"max": 0.20284608167906604,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.2650489116833342e-06,
"min": 3.2650489116833342e-06,
"max": 0.00029534902655032496,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.795146735050002e-06,
"min": 9.795146735050002e-06,
"max": 0.0008442388685870499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10108831666666666,
"min": 0.10108831666666666,
"max": 0.198449675,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30326495,
"min": 0.20733505000000005,
"max": 0.5814129500000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.430700166666669e-05,
"min": 6.430700166666669e-05,
"max": 0.004922638782500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019292100500000007,
"min": 0.00019292100500000007,
"max": 0.014072506205000002,
"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": "1701630401",
"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=Huggy --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1701632716"
},
"total": 2315.297405572,
"count": 1,
"self": 0.4448785719996522,
"children": {
"run_training.setup": {
"total": 0.05917816200008019,
"count": 1,
"self": 0.05917816200008019
},
"TrainerController.start_learning": {
"total": 2314.7933488380004,
"count": 1,
"self": 4.402252849063643,
"children": {
"TrainerController._reset_env": {
"total": 3.542613770999992,
"count": 1,
"self": 3.542613770999992
},
"TrainerController.advance": {
"total": 2306.7452257549367,
"count": 231377,
"self": 4.412774500832256,
"children": {
"env_step": {
"total": 1828.0634841470887,
"count": 231377,
"self": 1511.6825137610476,
"children": {
"SubprocessEnvManager._take_step": {
"total": 313.6896392759211,
"count": 231377,
"self": 15.871094279787144,
"children": {
"TorchPolicy.evaluate": {
"total": 297.81854499613394,
"count": 222940,
"self": 297.81854499613394
}
}
},
"workers": {
"total": 2.6913311101199042,
"count": 231377,
"self": 0.0,
"children": {
"worker_root": {
"total": 2307.132983479025,
"count": 231377,
"is_parallel": true,
"self": 1076.429939877079,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008205580001003909,
"count": 1,
"is_parallel": true,
"self": 0.00022137400014798914,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005991839999524018,
"count": 2,
"is_parallel": true,
"self": 0.0005991839999524018
}
}
},
"UnityEnvironment.step": {
"total": 0.04436038799997277,
"count": 1,
"is_parallel": true,
"self": 0.000296389000027375,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022227599993129843,
"count": 1,
"is_parallel": true,
"self": 0.00022227599993129843
},
"communicator.exchange": {
"total": 0.04317072300000291,
"count": 1,
"is_parallel": true,
"self": 0.04317072300000291
},
"steps_from_proto": {
"total": 0.0006710000000111904,
"count": 1,
"is_parallel": true,
"self": 0.00017678899985185126,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004942110001593392,
"count": 2,
"is_parallel": true,
"self": 0.0004942110001593392
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1230.7030436019459,
"count": 231376,
"is_parallel": true,
"self": 39.39684356992257,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.6994324259997,
"count": 231376,
"is_parallel": true,
"self": 81.6994324259997
},
"communicator.exchange": {
"total": 1022.7098848309884,
"count": 231376,
"is_parallel": true,
"self": 1022.7098848309884
},
"steps_from_proto": {
"total": 86.89688277503512,
"count": 231376,
"is_parallel": true,
"self": 30.098811843964768,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.798070931070356,
"count": 462752,
"is_parallel": true,
"self": 56.798070931070356
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 474.26896710701567,
"count": 231377,
"self": 6.778121462972308,
"children": {
"process_trajectory": {
"total": 143.9640446630426,
"count": 231377,
"self": 142.71695740604218,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2470872570004303,
"count": 10,
"self": 1.2470872570004303
}
}
},
"_update_policy": {
"total": 323.52680098100075,
"count": 97,
"self": 261.2708025690067,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.25599841199403,
"count": 2910,
"self": 62.25599841199403
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.239999260695186e-07,
"count": 1,
"self": 8.239999260695186e-07
},
"TrainerController._save_models": {
"total": 0.10325563900005363,
"count": 1,
"self": 0.0017050559999916004,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10155058300006203,
"count": 1,
"self": 0.10155058300006203
}
}
}
}
}
}
}