ppo-Huggy / run_logs /timers.json
gpfl's picture
Huggy is trained!
afef65d
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4021621942520142,
"min": 1.4021621942520142,
"max": 1.424591302871704,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69073.3125,
"min": 68598.21875,
"max": 75962.9375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 80.66830065359477,
"min": 79.13141025641026,
"max": 413.3471074380165,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49369.0,
"min": 48767.0,
"max": 50031.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999996.0,
"min": 49858.0,
"max": 1999996.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999996.0,
"min": 49858.0,
"max": 1999996.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3901312351226807,
"min": 0.11353088915348053,
"max": 2.514772891998291,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1462.76025390625,
"min": 13.623706817626953,
"max": 1529.28564453125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.662933093562625,
"min": 1.7104992806911468,
"max": 4.048756767058093,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2241.7150532603264,
"min": 205.25991368293762,
"max": 2417.1077899336815,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.662933093562625,
"min": 1.7104992806911468,
"max": 4.048756767058093,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2241.7150532603264,
"min": 205.25991368293762,
"max": 2417.1077899336815,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.02056895320614179,
"min": 0.014047070471214182,
"max": 0.02118139308877289,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.06170685961842537,
"min": 0.02873704960657051,
"max": 0.06170685961842537,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05727534422443973,
"min": 0.021491006202995776,
"max": 0.062244363874197,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1718260326733192,
"min": 0.04298201240599155,
"max": 0.17298892624676226,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.716998761033333e-06,
"min": 3.716998761033333e-06,
"max": 0.0002953851015383,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.11509962831e-05,
"min": 1.11509962831e-05,
"max": 0.0008444485685171498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10123896666666667,
"min": 0.10123896666666667,
"max": 0.19846170000000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3037169,
"min": 0.20767545000000004,
"max": 0.5814828499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.182443666666669e-05,
"min": 7.182443666666669e-05,
"max": 0.00492323883,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021547331000000005,
"min": 0.00021547331000000005,
"max": 0.014075994214999998,
"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": "1671393661",
"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": "1671395858"
},
"total": 2197.3851964600003,
"count": 1,
"self": 0.38859834400045656,
"children": {
"run_training.setup": {
"total": 0.11213093599997137,
"count": 1,
"self": 0.11213093599997137
},
"TrainerController.start_learning": {
"total": 2196.88446718,
"count": 1,
"self": 3.788703265042841,
"children": {
"TrainerController._reset_env": {
"total": 7.300025473000005,
"count": 1,
"self": 7.300025473000005
},
"TrainerController.advance": {
"total": 2185.682286103957,
"count": 232866,
"self": 4.025323375125936,
"children": {
"env_step": {
"total": 1717.741127096041,
"count": 232866,
"self": 1445.6546640251026,
"children": {
"SubprocessEnvManager._take_step": {
"total": 269.51316602101133,
"count": 232866,
"self": 13.93911571492572,
"children": {
"TorchPolicy.evaluate": {
"total": 255.5740503060856,
"count": 222883,
"self": 64.53412550998837,
"children": {
"TorchPolicy.sample_actions": {
"total": 191.03992479609724,
"count": 222883,
"self": 191.03992479609724
}
}
}
}
},
"workers": {
"total": 2.5732970499270778,
"count": 232866,
"self": 0.0,
"children": {
"worker_root": {
"total": 2189.1141875080352,
"count": 232866,
"is_parallel": true,
"self": 993.8752348108915,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020564840000361073,
"count": 1,
"is_parallel": true,
"self": 0.0003720830002293951,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016844009998067122,
"count": 2,
"is_parallel": true,
"self": 0.0016844009998067122
}
}
},
"UnityEnvironment.step": {
"total": 0.027679005999971196,
"count": 1,
"is_parallel": true,
"self": 0.0002984290000540568,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00017807199992603273,
"count": 1,
"is_parallel": true,
"self": 0.00017807199992603273
},
"communicator.exchange": {
"total": 0.02641716699997687,
"count": 1,
"is_parallel": true,
"self": 0.02641716699997687
},
"steps_from_proto": {
"total": 0.0007853380000142351,
"count": 1,
"is_parallel": true,
"self": 0.00026271799993082823,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005226200000834069,
"count": 2,
"is_parallel": true,
"self": 0.0005226200000834069
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1195.2389526971438,
"count": 232865,
"is_parallel": true,
"self": 34.90554269025256,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 76.39838251793753,
"count": 232865,
"is_parallel": true,
"self": 76.39838251793753
},
"communicator.exchange": {
"total": 990.2129788219607,
"count": 232865,
"is_parallel": true,
"self": 990.2129788219607
},
"steps_from_proto": {
"total": 93.7220486669928,
"count": 232865,
"is_parallel": true,
"self": 38.74422449212409,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.977824174868715,
"count": 465730,
"is_parallel": true,
"self": 54.977824174868715
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 463.9158356327897,
"count": 232866,
"self": 5.915571993801791,
"children": {
"process_trajectory": {
"total": 147.81063299998561,
"count": 232866,
"self": 146.5156705369851,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2949624630005019,
"count": 10,
"self": 1.2949624630005019
}
}
},
"_update_policy": {
"total": 310.1896306390023,
"count": 97,
"self": 257.3645771709902,
"children": {
"TorchPPOOptimizer.update": {
"total": 52.82505346801213,
"count": 2910,
"self": 52.82505346801213
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0870003279705998e-06,
"count": 1,
"self": 1.0870003279705998e-06
},
"TrainerController._save_models": {
"total": 0.11345125099978759,
"count": 1,
"self": 0.001850022999860812,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11160122799992678,
"count": 1,
"self": 0.11160122799992678
}
}
}
}
}
}
}