ppo-Huggy / run_logs /timers.json
omerfarukonge's picture
Huggy
51b2053 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.398000717163086,
"min": 1.398000717163086,
"max": 1.4254776239395142,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69806.3671875,
"min": 68060.046875,
"max": 76387.7109375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 67.57808219178082,
"min": 65.96380697050938,
"max": 373.95522388059703,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49332.0,
"min": 49074.0,
"max": 50110.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999977.0,
"min": 49951.0,
"max": 1999977.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999977.0,
"min": 49951.0,
"max": 1999977.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.505814790725708,
"min": 0.019117262214422226,
"max": 2.56961989402771,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1829.2447509765625,
"min": 2.542595863342285,
"max": 1887.2398681640625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8770266094436385,
"min": 1.933868830365346,
"max": 4.109421387813011,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2830.229424893856,
"min": 257.204554438591,
"max": 2982.8359019756317,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8770266094436385,
"min": 1.933868830365346,
"max": 4.109421387813011,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2830.229424893856,
"min": 257.204554438591,
"max": 2982.8359019756317,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01868565439610595,
"min": 0.012768399909934183,
"max": 0.02121679118523995,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05605696318831785,
"min": 0.025536799819868367,
"max": 0.06166142025297934,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06466252584424284,
"min": 0.023317959252744914,
"max": 0.06466252584424284,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.19398757753272852,
"min": 0.04663591850548983,
"max": 0.19398757753272852,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.034398655233335e-06,
"min": 4.034398655233335e-06,
"max": 0.0002953413015529,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.2103195965700006e-05,
"min": 1.2103195965700006e-05,
"max": 0.0008442861185712998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10134476666666668,
"min": 0.10134476666666668,
"max": 0.19844710000000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30403430000000004,
"min": 0.2078289000000001,
"max": 0.5814287,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.710385666666669e-05,
"min": 7.710385666666669e-05,
"max": 0.00492251029,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00023131157000000008,
"min": 0.00023131157000000008,
"max": 0.014073292130000001,
"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": "1740899912",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1740902721"
},
"total": 2809.1495194060003,
"count": 1,
"self": 0.43771545000072365,
"children": {
"run_training.setup": {
"total": 0.033423901999981354,
"count": 1,
"self": 0.033423901999981354
},
"TrainerController.start_learning": {
"total": 2808.6783800539997,
"count": 1,
"self": 5.420138768963625,
"children": {
"TrainerController._reset_env": {
"total": 3.3192292610000322,
"count": 1,
"self": 3.3192292610000322
},
"TrainerController.advance": {
"total": 2799.8240611100355,
"count": 234336,
"self": 5.514965923060572,
"children": {
"env_step": {
"total": 2263.621233412009,
"count": 234336,
"self": 1778.0794231351185,
"children": {
"SubprocessEnvManager._take_step": {
"total": 482.12541680089396,
"count": 234336,
"self": 18.460182843923576,
"children": {
"TorchPolicy.evaluate": {
"total": 463.6652339569704,
"count": 222928,
"self": 463.6652339569704
}
}
},
"workers": {
"total": 3.4163934759966423,
"count": 234336,
"self": 0.0,
"children": {
"worker_root": {
"total": 2800.146812880222,
"count": 234336,
"is_parallel": true,
"self": 1358.305375635155,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0012318889999960447,
"count": 1,
"is_parallel": true,
"self": 0.00030577399991216225,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009261150000838825,
"count": 2,
"is_parallel": true,
"self": 0.0009261150000838825
}
}
},
"UnityEnvironment.step": {
"total": 0.03624303299989151,
"count": 1,
"is_parallel": true,
"self": 0.0003763089998756186,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002199049999944691,
"count": 1,
"is_parallel": true,
"self": 0.0002199049999944691
},
"communicator.exchange": {
"total": 0.03478406299996095,
"count": 1,
"is_parallel": true,
"self": 0.03478406299996095
},
"steps_from_proto": {
"total": 0.0008627560000604717,
"count": 1,
"is_parallel": true,
"self": 0.0002474340000162556,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006153220000442161,
"count": 2,
"is_parallel": true,
"self": 0.0006153220000442161
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1441.841437245067,
"count": 234335,
"is_parallel": true,
"self": 41.566791432003356,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 91.31764978293086,
"count": 234335,
"is_parallel": true,
"self": 91.31764978293086
},
"communicator.exchange": {
"total": 1209.6989772892389,
"count": 234335,
"is_parallel": true,
"self": 1209.6989772892389
},
"steps_from_proto": {
"total": 99.25801874089382,
"count": 234335,
"is_parallel": true,
"self": 36.278272758730395,
"children": {
"_process_rank_one_or_two_observation": {
"total": 62.97974598216342,
"count": 468670,
"is_parallel": true,
"self": 62.97974598216342
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 530.6878617749658,
"count": 234336,
"self": 8.04521708085042,
"children": {
"process_trajectory": {
"total": 198.36717669411576,
"count": 234336,
"self": 196.9870106321158,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3801660619999438,
"count": 10,
"self": 1.3801660619999438
}
}
},
"_update_policy": {
"total": 324.2754679999996,
"count": 97,
"self": 256.3753937099948,
"children": {
"TorchPPOOptimizer.update": {
"total": 67.9000742900048,
"count": 2910,
"self": 67.9000742900048
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1650004125840496e-06,
"count": 1,
"self": 1.1650004125840496e-06
},
"TrainerController._save_models": {
"total": 0.11494974900006127,
"count": 1,
"self": 0.0018990349999512546,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11305071400011002,
"count": 1,
"self": 0.11305071400011002
}
}
}
}
}
}
}