ppo-Huggy / run_logs /timers.json
Logii33's picture
Huggy
896f369 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4067401885986328,
"min": 1.4067401885986328,
"max": 1.4257385730743408,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69428.2578125,
"min": 68785.3828125,
"max": 75847.5625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 109.65033407572383,
"min": 86.26444833625219,
"max": 396.0952380952381,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49233.0,
"min": 48939.0,
"max": 50162.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999985.0,
"min": 49518.0,
"max": 1999985.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999985.0,
"min": 49518.0,
"max": 1999985.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.2811553478240967,
"min": -0.04490596428513527,
"max": 2.4637222290039062,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1024.23876953125,
"min": -5.613245487213135,
"max": 1391.347900390625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.3842566707617454,
"min": 1.7489365303516389,
"max": 3.9488800377115725,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1519.5312451720238,
"min": 218.61706629395485,
"max": 2189.8018813729286,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.3842566707617454,
"min": 1.7489365303516389,
"max": 3.9488800377115725,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1519.5312451720238,
"min": 218.61706629395485,
"max": 2189.8018813729286,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01728174465905694,
"min": 0.014388262777902127,
"max": 0.019674111961285237,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.051845233977170814,
"min": 0.028776525555804254,
"max": 0.059022335883855706,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04734967909753323,
"min": 0.024458611197769643,
"max": 0.062117216239372886,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14204903729259968,
"min": 0.048917222395539285,
"max": 0.18635164871811866,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.474198841966668e-06,
"min": 3.474198841966668e-06,
"max": 0.0002953005015665,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0422596525900004e-05,
"min": 1.0422596525900004e-05,
"max": 0.0008439601686799502,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10115803333333336,
"min": 0.10115803333333336,
"max": 0.19843350000000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3034741000000001,
"min": 0.2074922,
"max": 0.5813200499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.778586333333336e-05,
"min": 6.778586333333336e-05,
"max": 0.00492183165,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020335759000000007,
"min": 0.00020335759000000007,
"max": 0.014067870495,
"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": "1721671580",
"python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1721673969"
},
"total": 2389.430650511,
"count": 1,
"self": 0.43702392199975293,
"children": {
"run_training.setup": {
"total": 0.05889567500003068,
"count": 1,
"self": 0.05889567500003068
},
"TrainerController.start_learning": {
"total": 2388.9347309140003,
"count": 1,
"self": 4.3380969658801405,
"children": {
"TrainerController._reset_env": {
"total": 2.9331078230000003,
"count": 1,
"self": 2.9331078230000003
},
"TrainerController.advance": {
"total": 2381.53451195812,
"count": 231846,
"self": 4.597128362152489,
"children": {
"env_step": {
"total": 1883.4396696540266,
"count": 231846,
"self": 1553.490927202899,
"children": {
"SubprocessEnvManager._take_step": {
"total": 327.12384687815074,
"count": 231846,
"self": 18.150752624051165,
"children": {
"TorchPolicy.evaluate": {
"total": 308.9730942540996,
"count": 223048,
"self": 308.9730942540996
}
}
},
"workers": {
"total": 2.824895572976857,
"count": 231846,
"self": 0.0,
"children": {
"worker_root": {
"total": 2381.7674229068543,
"count": 231846,
"is_parallel": true,
"self": 1133.2365084908226,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008554390001336287,
"count": 1,
"is_parallel": true,
"self": 0.00018690500019147294,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006685339999421558,
"count": 2,
"is_parallel": true,
"self": 0.0006685339999421558
}
}
},
"UnityEnvironment.step": {
"total": 0.02930156200000056,
"count": 1,
"is_parallel": true,
"self": 0.000367348000054335,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021637600002577528,
"count": 1,
"is_parallel": true,
"self": 0.00021637600002577528
},
"communicator.exchange": {
"total": 0.027965913999878467,
"count": 1,
"is_parallel": true,
"self": 0.027965913999878467
},
"steps_from_proto": {
"total": 0.0007519240000419813,
"count": 1,
"is_parallel": true,
"self": 0.00019376999989617616,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005581540001458052,
"count": 2,
"is_parallel": true,
"self": 0.0005581540001458052
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1248.5309144160317,
"count": 231845,
"is_parallel": true,
"self": 38.67504020698084,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.42755918504349,
"count": 231845,
"is_parallel": true,
"self": 79.42755918504349
},
"communicator.exchange": {
"total": 1041.3255325740072,
"count": 231845,
"is_parallel": true,
"self": 1041.3255325740072
},
"steps_from_proto": {
"total": 89.10278245000018,
"count": 231845,
"is_parallel": true,
"self": 31.864443987901723,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.238338462098454,
"count": 463690,
"is_parallel": true,
"self": 57.238338462098454
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 493.49771394194113,
"count": 231846,
"self": 7.055220152933089,
"children": {
"process_trajectory": {
"total": 155.00818164900943,
"count": 231846,
"self": 153.69385499400846,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3143266550009685,
"count": 10,
"self": 1.3143266550009685
}
}
},
"_update_policy": {
"total": 331.4343121399986,
"count": 97,
"self": 266.65333581599543,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.78097632400318,
"count": 2910,
"self": 64.78097632400318
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1530000847415067e-06,
"count": 1,
"self": 1.1530000847415067e-06
},
"TrainerController._save_models": {
"total": 0.12901301399961085,
"count": 1,
"self": 0.001970719999007997,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12704229400060285,
"count": 1,
"self": 0.12704229400060285
}
}
}
}
}
}
}