ppo-Huggy / run_logs /timers.json
BILOO237's picture
Huggy
98c419c verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.404239535331726,
"min": 1.404239535331726,
"max": 1.4296609163284302,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68178.640625,
"min": 68102.515625,
"max": 78034.9453125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 155.99683544303798,
"min": 96.48148148148148,
"max": 395.968253968254,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49295.0,
"min": 48882.0,
"max": 50217.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999992.0,
"min": 49462.0,
"max": 1999992.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999992.0,
"min": 49462.0,
"max": 1999992.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.1948623657226562,
"min": 0.09173031896352768,
"max": 2.3624374866485596,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 693.5765380859375,
"min": 11.466289520263672,
"max": 1202.0006103515625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.2734860683543774,
"min": 1.8666414070129393,
"max": 3.9810222146216403,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1034.4215975999832,
"min": 233.33017587661743,
"max": 1917.099036037922,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.2734860683543774,
"min": 1.8666414070129393,
"max": 3.9810222146216403,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1034.4215975999832,
"min": 233.33017587661743,
"max": 1917.099036037922,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017216641832116387,
"min": 0.01188554325720664,
"max": 0.021900631113870382,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.034433283664232775,
"min": 0.02377108651441328,
"max": 0.05480162679159548,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.03857815554365515,
"min": 0.022517933634420235,
"max": 0.06295787253313595,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.0771563110873103,
"min": 0.04503586726884047,
"max": 0.18887361759940785,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.181198606300008e-06,
"min": 4.181198606300008e-06,
"max": 0.00029535735154754997,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.362397212600016e-06,
"min": 8.362397212600016e-06,
"max": 0.00084431806856065,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1013937,
"min": 0.1013937,
"max": 0.19845245,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.2027874,
"min": 0.2027874,
"max": 0.5814393500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.954563000000016e-05,
"min": 7.954563000000016e-05,
"max": 0.004922777255,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00015909126000000033,
"min": 0.00015909126000000033,
"max": 0.014073823565000003,
"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": "1723283756",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "1723286074"
},
"total": 2317.922488649,
"count": 1,
"self": 0.4396391630002654,
"children": {
"run_training.setup": {
"total": 0.0585624599999619,
"count": 1,
"self": 0.0585624599999619
},
"TrainerController.start_learning": {
"total": 2317.424287026,
"count": 1,
"self": 4.261960407940023,
"children": {
"TrainerController._reset_env": {
"total": 2.7525112270000136,
"count": 1,
"self": 2.7525112270000136
},
"TrainerController.advance": {
"total": 2310.29485294206,
"count": 230484,
"self": 4.5387883630373835,
"children": {
"env_step": {
"total": 1835.1522936749968,
"count": 230484,
"self": 1506.3092033740613,
"children": {
"SubprocessEnvManager._take_step": {
"total": 326.02501971393497,
"count": 230484,
"self": 16.91585023995242,
"children": {
"TorchPolicy.evaluate": {
"total": 309.10916947398255,
"count": 223004,
"self": 309.10916947398255
}
}
},
"workers": {
"total": 2.818070587000534,
"count": 230484,
"self": 0.0,
"children": {
"worker_root": {
"total": 2310.2443192789233,
"count": 230484,
"is_parallel": true,
"self": 1093.9237862469724,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000851624000006268,
"count": 1,
"is_parallel": true,
"self": 0.0002129399999830639,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006386840000232041,
"count": 2,
"is_parallel": true,
"self": 0.0006386840000232041
}
}
},
"UnityEnvironment.step": {
"total": 0.03533193399994161,
"count": 1,
"is_parallel": true,
"self": 0.0004159349998644757,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022726500003500405,
"count": 1,
"is_parallel": true,
"self": 0.00022726500003500405
},
"communicator.exchange": {
"total": 0.0338185360000125,
"count": 1,
"is_parallel": true,
"self": 0.0338185360000125
},
"steps_from_proto": {
"total": 0.0008701980000296317,
"count": 1,
"is_parallel": true,
"self": 0.00024174600002879743,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006284520000008342,
"count": 2,
"is_parallel": true,
"self": 0.0006284520000008342
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1216.3205330319508,
"count": 230483,
"is_parallel": true,
"self": 37.353047212924366,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.46281698500923,
"count": 230483,
"is_parallel": true,
"self": 79.46281698500923
},
"communicator.exchange": {
"total": 1012.4669883951186,
"count": 230483,
"is_parallel": true,
"self": 1012.4669883951186
},
"steps_from_proto": {
"total": 87.03768043889852,
"count": 230483,
"is_parallel": true,
"self": 30.63264847896687,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.40503195993165,
"count": 460966,
"is_parallel": true,
"self": 56.40503195993165
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 470.6037709040261,
"count": 230484,
"self": 6.795220435993883,
"children": {
"process_trajectory": {
"total": 138.07103317803148,
"count": 230484,
"self": 136.75022324403108,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3208099340004082,
"count": 10,
"self": 1.3208099340004082
}
}
},
"_update_policy": {
"total": 325.7375172900007,
"count": 96,
"self": 262.91482110200764,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.822696187993074,
"count": 2880,
"self": 62.822696187993074
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.099999260797631e-07,
"count": 1,
"self": 9.099999260797631e-07
},
"TrainerController._save_models": {
"total": 0.11496153899997807,
"count": 1,
"self": 0.0020839290000367328,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11287760999994134,
"count": 1,
"self": 0.11287760999994134
}
}
}
}
}
}
}