ppo-Huggy / run_logs /timers.json
rgny's picture
Huggy
412679b
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4045181274414062,
"min": 1.404491662979126,
"max": 1.426081657409668,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69206.2265625,
"min": 67791.2109375,
"max": 77803.84375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 103.0977130977131,
"min": 85.67764298093587,
"max": 420.57142857142856,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49590.0,
"min": 48873.0,
"max": 50141.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999978.0,
"min": 49583.0,
"max": 1999978.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999978.0,
"min": 49583.0,
"max": 1999978.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.419212818145752,
"min": 0.06379568576812744,
"max": 2.4778072834014893,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1163.641357421875,
"min": 7.527891159057617,
"max": 1395.1021728515625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6707988281012076,
"min": 1.8762000650167465,
"max": 3.909895341179588,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1765.654236316681,
"min": 221.3916076719761,
"max": 2208.47220826149,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6707988281012076,
"min": 1.8762000650167465,
"max": 3.909895341179588,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1765.654236316681,
"min": 221.3916076719761,
"max": 2208.47220826149,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.0165222702038995,
"min": 0.013417037859350483,
"max": 0.019407900826384623,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0495668106116985,
"min": 0.026834075718700966,
"max": 0.05648652806363923,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04872676088578171,
"min": 0.023572749799738328,
"max": 0.05748948423812787,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14618028265734515,
"min": 0.047145499599476656,
"max": 0.1712358258664608,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.256148914650011e-06,
"min": 3.256148914650011e-06,
"max": 0.00029530912656362503,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.768446743950034e-06,
"min": 9.768446743950034e-06,
"max": 0.0008441251686249498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10108535000000002,
"min": 0.10108535000000002,
"max": 0.198436375,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30325605000000005,
"min": 0.20729955000000003,
"max": 0.5813750500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.41589650000002e-05,
"min": 6.41589650000002e-05,
"max": 0.004921975112500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001924768950000006,
"min": 0.0001924768950000006,
"max": 0.014070614995000001,
"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": "1702883719",
"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": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1702886267"
},
"total": 2547.6739601950003,
"count": 1,
"self": 0.44658010999955877,
"children": {
"run_training.setup": {
"total": 0.049292075000039404,
"count": 1,
"self": 0.049292075000039404
},
"TrainerController.start_learning": {
"total": 2547.1780880100005,
"count": 1,
"self": 4.56554388184577,
"children": {
"TrainerController._reset_env": {
"total": 3.3363978700001553,
"count": 1,
"self": 3.3363978700001553
},
"TrainerController.advance": {
"total": 2539.1613697801545,
"count": 231979,
"self": 5.032295083089139,
"children": {
"env_step": {
"total": 2026.9448521499262,
"count": 231979,
"self": 1679.4195558767083,
"children": {
"SubprocessEnvManager._take_step": {
"total": 344.46861949009417,
"count": 231979,
"self": 17.41683226204691,
"children": {
"TorchPolicy.evaluate": {
"total": 327.05178722804726,
"count": 223012,
"self": 327.05178722804726
}
}
},
"workers": {
"total": 3.0566767831237485,
"count": 231979,
"self": 0.0,
"children": {
"worker_root": {
"total": 2539.7557688279967,
"count": 231979,
"is_parallel": true,
"self": 1176.969853543956,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0006541429997923842,
"count": 1,
"is_parallel": true,
"self": 0.00023224399978971633,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004218990000026679,
"count": 2,
"is_parallel": true,
"self": 0.0004218990000026679
}
}
},
"UnityEnvironment.step": {
"total": 0.05913882599998033,
"count": 1,
"is_parallel": true,
"self": 0.0003493780000098923,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019441600011305127,
"count": 1,
"is_parallel": true,
"self": 0.00019441600011305127
},
"communicator.exchange": {
"total": 0.05786538400002428,
"count": 1,
"is_parallel": true,
"self": 0.05786538400002428
},
"steps_from_proto": {
"total": 0.0007296479998331051,
"count": 1,
"is_parallel": true,
"self": 0.000209690999781742,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005199570000513631,
"count": 2,
"is_parallel": true,
"self": 0.0005199570000513631
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1362.7859152840406,
"count": 231978,
"is_parallel": true,
"self": 42.32139681117155,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 89.05646897608153,
"count": 231978,
"is_parallel": true,
"self": 89.05646897608153
},
"communicator.exchange": {
"total": 1137.1740567938477,
"count": 231978,
"is_parallel": true,
"self": 1137.1740567938477
},
"steps_from_proto": {
"total": 94.23399270293976,
"count": 231978,
"is_parallel": true,
"self": 34.909457678199715,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.324535024740044,
"count": 463956,
"is_parallel": true,
"self": 59.324535024740044
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 507.1842225471389,
"count": 231979,
"self": 7.317108356094423,
"children": {
"process_trajectory": {
"total": 157.5987917750433,
"count": 231979,
"self": 156.34456385104272,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2542279240005882,
"count": 10,
"self": 1.2542279240005882
}
}
},
"_update_policy": {
"total": 342.2683224160012,
"count": 97,
"self": 277.1423687909921,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.12595362500906,
"count": 2910,
"self": 65.12595362500906
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.659999366500415e-07,
"count": 1,
"self": 8.659999366500415e-07
},
"TrainerController._save_models": {
"total": 0.11477561199990305,
"count": 1,
"self": 0.0019512429998940206,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11282436900000903,
"count": 1,
"self": 0.11282436900000903
}
}
}
}
}
}
}