ppo-Huggy / run_logs /timers.json
Atlasbot's picture
Huggy
8f209a9 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.401501178741455,
"min": 1.401501178741455,
"max": 1.426831603050232,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68464.734375,
"min": 68304.375,
"max": 76609.3359375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 99.23658051689861,
"min": 79.5096463022508,
"max": 362.68840579710144,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49916.0,
"min": 48873.0,
"max": 50051.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999715.0,
"min": 49733.0,
"max": 1999715.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999715.0,
"min": 49733.0,
"max": 1999715.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3639278411865234,
"min": 0.08976549655199051,
"max": 2.456310987472534,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1189.0556640625,
"min": 12.297872543334961,
"max": 1491.927978515625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.542842928149828,
"min": 1.7606120953594682,
"max": 3.913482302209226,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1782.0499928593636,
"min": 241.20385706424713,
"max": 2311.87002235651,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.542842928149828,
"min": 1.7606120953594682,
"max": 3.913482302209226,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1782.0499928593636,
"min": 241.20385706424713,
"max": 2311.87002235651,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.020070738960445547,
"min": 0.012782223651205033,
"max": 0.02106887085149841,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.06021221688133664,
"min": 0.025564447302410066,
"max": 0.06021221688133664,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04872336097889476,
"min": 0.021671058361728987,
"max": 0.06068208590149879,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14617008293668426,
"min": 0.043342116723457974,
"max": 0.18027891777455807,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.54384881875e-06,
"min": 3.54384881875e-06,
"max": 0.00029531152656282495,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.063154645625e-05,
"min": 1.063154645625e-05,
"max": 0.0008441683686105499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10118125,
"min": 0.10118125,
"max": 0.19843717500000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30354375,
"min": 0.20751425,
"max": 0.58138945,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.894437500000004e-05,
"min": 6.894437500000004e-05,
"max": 0.004922015032500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020683312500000011,
"min": 0.00020683312500000011,
"max": 0.014071333555,
"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": "1730658785",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1730661324"
},
"total": 2539.0118016809997,
"count": 1,
"self": 0.4316421969997464,
"children": {
"run_training.setup": {
"total": 0.05767247599987968,
"count": 1,
"self": 0.05767247599987968
},
"TrainerController.start_learning": {
"total": 2538.522487008,
"count": 1,
"self": 4.754451644034816,
"children": {
"TrainerController._reset_env": {
"total": 4.852820005000012,
"count": 1,
"self": 4.852820005000012
},
"TrainerController.advance": {
"total": 2528.809171514965,
"count": 232383,
"self": 4.7567472640248525,
"children": {
"env_step": {
"total": 2006.4098565100417,
"count": 232383,
"self": 1583.2601970451212,
"children": {
"SubprocessEnvManager._take_step": {
"total": 420.2729005180049,
"count": 232383,
"self": 16.037152255099045,
"children": {
"TorchPolicy.evaluate": {
"total": 404.2357482629059,
"count": 222920,
"self": 404.2357482629059
}
}
},
"workers": {
"total": 2.8767589469155155,
"count": 232383,
"self": 0.0,
"children": {
"worker_root": {
"total": 2530.975816059909,
"count": 232383,
"is_parallel": true,
"self": 1241.356270738858,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000832240000136153,
"count": 1,
"is_parallel": true,
"self": 0.0002360540001973277,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005961859999388253,
"count": 2,
"is_parallel": true,
"self": 0.0005961859999388253
}
}
},
"UnityEnvironment.step": {
"total": 0.02834416200016676,
"count": 1,
"is_parallel": true,
"self": 0.00037250800028232334,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001994350000131817,
"count": 1,
"is_parallel": true,
"self": 0.0001994350000131817
},
"communicator.exchange": {
"total": 0.027000049999969633,
"count": 1,
"is_parallel": true,
"self": 0.027000049999969633
},
"steps_from_proto": {
"total": 0.0007721689999016235,
"count": 1,
"is_parallel": true,
"self": 0.0002007690000027651,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005713999998988584,
"count": 2,
"is_parallel": true,
"self": 0.0005713999998988584
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1289.619545321051,
"count": 232382,
"is_parallel": true,
"self": 38.688323565999326,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 87.8142992570447,
"count": 232382,
"is_parallel": true,
"self": 87.8142992570447
},
"communicator.exchange": {
"total": 1070.9352847979942,
"count": 232382,
"is_parallel": true,
"self": 1070.9352847979942
},
"steps_from_proto": {
"total": 92.18163770001274,
"count": 232382,
"is_parallel": true,
"self": 34.85974358010094,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.3218941199118,
"count": 464764,
"is_parallel": true,
"self": 57.3218941199118
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 517.6425677408984,
"count": 232383,
"self": 6.949128956857521,
"children": {
"process_trajectory": {
"total": 178.0582398750414,
"count": 232383,
"self": 176.7526713260404,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3055685490010092,
"count": 10,
"self": 1.3055685490010092
}
}
},
"_update_policy": {
"total": 332.6351989089994,
"count": 97,
"self": 267.1997189960214,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.43547991297805,
"count": 2910,
"self": 65.43547991297805
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.500004125584383e-07,
"count": 1,
"self": 9.500004125584383e-07
},
"TrainerController._save_models": {
"total": 0.10604289399998379,
"count": 1,
"self": 0.0020861309999418154,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10395676300004197,
"count": 1,
"self": 0.10395676300004197
}
}
}
}
}
}
}