ppo-Huggy / run_logs /timers.json
nemanjar's picture
Huggy
d7608e3
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4038513898849487,
"min": 1.4038513898849487,
"max": 1.4303348064422607,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70448.0703125,
"min": 67525.3828125,
"max": 78119.765625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 110.07142857142857,
"min": 85.86260869565217,
"max": 406.2926829268293,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49312.0,
"min": 48895.0,
"max": 50109.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999942.0,
"min": 49347.0,
"max": 1999942.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999942.0,
"min": 49347.0,
"max": 1999942.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.393514394760132,
"min": 0.16196852922439575,
"max": 2.4514849185943604,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1072.29443359375,
"min": 19.760160446166992,
"max": 1387.478271484375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7713667560767914,
"min": 1.7881710805365296,
"max": 3.9078024508678806,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1689.5723067224026,
"min": 218.15687182545662,
"max": 2207.9083847403526,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7713667560767914,
"min": 1.7881710805365296,
"max": 3.9078024508678806,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1689.5723067224026,
"min": 218.15687182545662,
"max": 2207.9083847403526,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016868479119148103,
"min": 0.012677534156440136,
"max": 0.020984544543898663,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05060543735744431,
"min": 0.025355068312880272,
"max": 0.05866004007402808,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05924192695981926,
"min": 0.018856290820986034,
"max": 0.062297125202086225,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17772578087945778,
"min": 0.03771258164197207,
"max": 0.18689137560625868,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.240948919716673e-06,
"min": 3.240948919716673e-06,
"max": 0.00029534287655237493,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.72284675915002e-06,
"min": 9.72284675915002e-06,
"max": 0.0008442889685703499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10108028333333334,
"min": 0.10108028333333334,
"max": 0.19844762500000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30324085,
"min": 0.2072949,
"max": 0.58142965,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.390613833333342e-05,
"min": 6.390613833333342e-05,
"max": 0.004922536487499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019171841500000025,
"min": 0.00019171841500000025,
"max": 0.014073339535,
"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": "1672219794",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1672222051"
},
"total": 2256.780276634,
"count": 1,
"self": 0.389678441000342,
"children": {
"run_training.setup": {
"total": 0.11132645899999716,
"count": 1,
"self": 0.11132645899999716
},
"TrainerController.start_learning": {
"total": 2256.279271734,
"count": 1,
"self": 3.847994861902862,
"children": {
"TrainerController._reset_env": {
"total": 8.53353114600003,
"count": 1,
"self": 8.53353114600003
},
"TrainerController.advance": {
"total": 2243.7712436730967,
"count": 231498,
"self": 4.1060848772763165,
"children": {
"env_step": {
"total": 1770.6979596139502,
"count": 231498,
"self": 1487.6908135090653,
"children": {
"SubprocessEnvManager._take_step": {
"total": 280.4375489209493,
"count": 231498,
"self": 14.301774560911383,
"children": {
"TorchPolicy.evaluate": {
"total": 266.13577436003794,
"count": 222986,
"self": 66.19182813603328,
"children": {
"TorchPolicy.sample_actions": {
"total": 199.94394622400466,
"count": 222986,
"self": 199.94394622400466
}
}
}
}
},
"workers": {
"total": 2.5695971839355707,
"count": 231498,
"self": 0.0,
"children": {
"worker_root": {
"total": 2248.318264016038,
"count": 231498,
"is_parallel": true,
"self": 1028.172193458096,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0021106609999606007,
"count": 1,
"is_parallel": true,
"self": 0.00035130999992816214,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017593510000324386,
"count": 2,
"is_parallel": true,
"self": 0.0017593510000324386
}
}
},
"UnityEnvironment.step": {
"total": 0.027432341999997334,
"count": 1,
"is_parallel": true,
"self": 0.0002738129999784178,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001811120000070332,
"count": 1,
"is_parallel": true,
"self": 0.0001811120000070332
},
"communicator.exchange": {
"total": 0.026281781000022875,
"count": 1,
"is_parallel": true,
"self": 0.026281781000022875
},
"steps_from_proto": {
"total": 0.0006956359999890083,
"count": 1,
"is_parallel": true,
"self": 0.0002524969999626592,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004431390000263491,
"count": 2,
"is_parallel": true,
"self": 0.0004431390000263491
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1220.146070557942,
"count": 231497,
"is_parallel": true,
"self": 34.70442003179346,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.16903018006724,
"count": 231497,
"is_parallel": true,
"self": 80.16903018006724
},
"communicator.exchange": {
"total": 1009.825563181945,
"count": 231497,
"is_parallel": true,
"self": 1009.825563181945
},
"steps_from_proto": {
"total": 95.44705716413631,
"count": 231497,
"is_parallel": true,
"self": 41.703490443997396,
"children": {
"_process_rank_one_or_two_observation": {
"total": 53.743566720138915,
"count": 462994,
"is_parallel": true,
"self": 53.743566720138915
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 468.96719918187,
"count": 231498,
"self": 6.056420415870718,
"children": {
"process_trajectory": {
"total": 147.4035348640004,
"count": 231498,
"self": 146.2521758490007,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1513590149996844,
"count": 10,
"self": 1.1513590149996844
}
}
},
"_update_policy": {
"total": 315.5072439019989,
"count": 97,
"self": 263.38410596000324,
"children": {
"TorchPPOOptimizer.update": {
"total": 52.12313794199565,
"count": 2910,
"self": 52.12313794199565
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1100000847363845e-06,
"count": 1,
"self": 1.1100000847363845e-06
},
"TrainerController._save_models": {
"total": 0.12650094300033743,
"count": 1,
"self": 0.0019384140005058725,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12456252899983156,
"count": 1,
"self": 0.12456252899983156
}
}
}
}
}
}
}