ppo-Huggy / run_logs /timers.json
Pranjal-666's picture
Huggy
f544f70
raw
history blame
17.5 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4007035493850708,
"min": 1.4007035493850708,
"max": 1.4290236234664917,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69906.3125,
"min": 68356.6328125,
"max": 78675.671875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 73.1511111111111,
"min": 69.50352609308885,
"max": 388.1782945736434,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49377.0,
"min": 48912.0,
"max": 50075.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999953.0,
"min": 49950.0,
"max": 1999953.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999953.0,
"min": 49950.0,
"max": 1999953.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4748973846435547,
"min": 0.11268042773008347,
"max": 2.5159926414489746,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1670.5556640625,
"min": 14.423094749450684,
"max": 1712.39990234375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.872824581993951,
"min": 1.9283744129352272,
"max": 4.04107736019378,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2614.1565928459167,
"min": 246.83192485570908,
"max": 2648.3317207098007,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.872824581993951,
"min": 1.9283744129352272,
"max": 4.04107736019378,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2614.1565928459167,
"min": 246.83192485570908,
"max": 2648.3317207098007,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014549982459963454,
"min": 0.012854810726033368,
"max": 0.020559830073034392,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.043649947379890364,
"min": 0.025709621452066737,
"max": 0.05551213017267098,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05767924193706777,
"min": 0.022050277578334013,
"max": 0.06238244616736968,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1730377258112033,
"min": 0.044100555156668025,
"max": 0.1850583955645561,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.001198666300002e-06,
"min": 4.001198666300002e-06,
"max": 0.0002953350015549999,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.2003595998900006e-05,
"min": 1.2003595998900006e-05,
"max": 0.0008441979186006999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10133369999999998,
"min": 0.10133369999999998,
"max": 0.19844499999999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30400109999999997,
"min": 0.20779315000000004,
"max": 0.5813993000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.655163000000002e-05,
"min": 7.655163000000002e-05,
"max": 0.004922405499999998,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022965489000000008,
"min": 0.00022965489000000008,
"max": 0.014071825070000004,
"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": "1687420899",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1687423311"
},
"total": 2411.690353327,
"count": 1,
"self": 0.6816599950002455,
"children": {
"run_training.setup": {
"total": 0.05035139500000696,
"count": 1,
"self": 0.05035139500000696
},
"TrainerController.start_learning": {
"total": 2410.9583419369997,
"count": 1,
"self": 4.309917647995462,
"children": {
"TrainerController._reset_env": {
"total": 4.138131774000044,
"count": 1,
"self": 4.138131774000044
},
"TrainerController.advance": {
"total": 2402.3258946220044,
"count": 232944,
"self": 4.361056714076767,
"children": {
"env_step": {
"total": 1862.392604064994,
"count": 232944,
"self": 1573.8098603050594,
"children": {
"SubprocessEnvManager._take_step": {
"total": 285.8655279959926,
"count": 232944,
"self": 16.780534115010596,
"children": {
"TorchPolicy.evaluate": {
"total": 269.084993880982,
"count": 222886,
"self": 269.084993880982
}
}
},
"workers": {
"total": 2.7172157639419083,
"count": 232944,
"self": 0.0,
"children": {
"worker_root": {
"total": 2403.0718009089587,
"count": 232944,
"is_parallel": true,
"self": 1113.8552742329819,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009061010000550596,
"count": 1,
"is_parallel": true,
"self": 0.000275261000183491,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006308399998715686,
"count": 2,
"is_parallel": true,
"self": 0.0006308399998715686
}
}
},
"UnityEnvironment.step": {
"total": 0.028363892000015767,
"count": 1,
"is_parallel": true,
"self": 0.0003388590000668046,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020398799995291483,
"count": 1,
"is_parallel": true,
"self": 0.00020398799995291483
},
"communicator.exchange": {
"total": 0.027067187000056947,
"count": 1,
"is_parallel": true,
"self": 0.027067187000056947
},
"steps_from_proto": {
"total": 0.0007538579999391004,
"count": 1,
"is_parallel": true,
"self": 0.0002158709999093844,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000537987000029716,
"count": 2,
"is_parallel": true,
"self": 0.000537987000029716
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1289.2165266759769,
"count": 232943,
"is_parallel": true,
"self": 39.52077431213843,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.59143620399345,
"count": 232943,
"is_parallel": true,
"self": 79.59143620399345
},
"communicator.exchange": {
"total": 1075.9456640948779,
"count": 232943,
"is_parallel": true,
"self": 1075.9456640948779
},
"steps_from_proto": {
"total": 94.1586520649671,
"count": 232943,
"is_parallel": true,
"self": 33.369984407888296,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.788667657078804,
"count": 465886,
"is_parallel": true,
"self": 60.788667657078804
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 535.5722338429338,
"count": 232944,
"self": 6.388626175942136,
"children": {
"process_trajectory": {
"total": 137.80939013099533,
"count": 232944,
"self": 136.41961310399483,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3897770270004912,
"count": 10,
"self": 1.3897770270004912
}
}
},
"_update_policy": {
"total": 391.3742175359963,
"count": 97,
"self": 331.97840346000135,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.39581407599496,
"count": 2910,
"self": 59.39581407599496
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2359996617306024e-06,
"count": 1,
"self": 1.2359996617306024e-06
},
"TrainerController._save_models": {
"total": 0.1843966569999793,
"count": 1,
"self": 0.002651810999850568,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18174484600012875,
"count": 1,
"self": 0.18174484600012875
}
}
}
}
}
}
}