ppo-Huggy / run_logs /timers.json
KidIkaros's picture
Huggy
781ae57 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4026272296905518,
"min": 1.4026272296905518,
"max": 1.4293477535247803,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71615.34375,
"min": 18719.767578125,
"max": 72698.046875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 80.59706362153344,
"min": 74.20178041543026,
"max": 354.54609929078015,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49406.0,
"min": 8883.0,
"max": 50012.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999929.0,
"min": 49774.0,
"max": 1999929.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999929.0,
"min": 49774.0,
"max": 1999929.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4763760566711426,
"min": 0.26555031538009644,
"max": 2.527196168899536,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1518.0185546875,
"min": 8.497610092163086,
"max": 1624.5517578125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9061286817950487,
"min": 2.149429928511381,
"max": 4.059109006475353,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2394.456881940365,
"min": 68.7817577123642,
"max": 2581.5933281183243,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9061286817950487,
"min": 2.149429928511381,
"max": 4.059109006475353,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2394.456881940365,
"min": 68.7817577123642,
"max": 2581.5933281183243,
"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
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017092270202798927,
"min": 0.013352871000461165,
"max": 0.02007966382920535,
"count": 39
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.051276810608396776,
"min": 0.02670574200092233,
"max": 0.06023899148761605,
"count": 39
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.055813864411579234,
"min": 0.022879454338302213,
"max": 0.06256111264228821,
"count": 39
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1674415932347377,
"min": 0.045758908676604426,
"max": 0.18229771355787913,
"count": 39
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.829298723599999e-06,
"min": 3.829298723599999e-06,
"max": 0.00028909762863412494,
"count": 39
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1487896170799997e-05,
"min": 1.1487896170799997e-05,
"max": 0.0008439636186788,
"count": 39
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10127639999999997,
"min": 0.10127639999999997,
"max": 0.19636587499999997,
"count": 39
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3038291999999999,
"min": 0.20768755000000003,
"max": 0.5813212000000001,
"count": 39
},
"Huggy.Policy.Beta.mean": {
"value": 7.369236e-05,
"min": 7.369236e-05,
"max": 0.0048186571625,
"count": 39
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022107707999999998,
"min": 0.00022107707999999998,
"max": 0.01406792788,
"count": 39
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1742317741",
"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 --resume",
"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": "1742320193"
},
"total": 2451.7719619279997,
"count": 1,
"self": 0.4775989639992986,
"children": {
"run_training.setup": {
"total": 0.020654959000239614,
"count": 1,
"self": 0.020654959000239614
},
"TrainerController.start_learning": {
"total": 2451.273708005,
"count": 1,
"self": 4.687259229918709,
"children": {
"TrainerController._reset_env": {
"total": 1.9770977870002753,
"count": 1,
"self": 1.9770977870002753
},
"TrainerController.advance": {
"total": 2444.4720607810814,
"count": 228293,
"self": 4.4931536332942414,
"children": {
"env_step": {
"total": 1951.98948933585,
"count": 228293,
"self": 1532.5820673647972,
"children": {
"SubprocessEnvManager._take_step": {
"total": 416.715392282053,
"count": 228293,
"self": 15.960703637239476,
"children": {
"TorchPolicy.evaluate": {
"total": 400.75468864481354,
"count": 218426,
"self": 400.75468864481354
}
}
},
"workers": {
"total": 2.69202968899981,
"count": 228293,
"self": 0.0,
"children": {
"worker_root": {
"total": 2443.794061309037,
"count": 228293,
"is_parallel": true,
"self": 1191.609514400891,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008675639996909013,
"count": 1,
"is_parallel": true,
"self": 0.0002536139995754638,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006139500001154374,
"count": 2,
"is_parallel": true,
"self": 0.0006139500001154374
}
}
},
"UnityEnvironment.step": {
"total": 0.03036577800003215,
"count": 1,
"is_parallel": true,
"self": 0.00026208999997834326,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021457799994095694,
"count": 1,
"is_parallel": true,
"self": 0.00021457799994095694
},
"communicator.exchange": {
"total": 0.029074002000015753,
"count": 1,
"is_parallel": true,
"self": 0.029074002000015753
},
"steps_from_proto": {
"total": 0.0008151080000970978,
"count": 1,
"is_parallel": true,
"self": 0.00032096099994305405,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004941470001540438,
"count": 2,
"is_parallel": true,
"self": 0.0004941470001540438
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1252.1845469081459,
"count": 228292,
"is_parallel": true,
"self": 36.1012616333046,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.63227219289456,
"count": 228292,
"is_parallel": true,
"self": 81.63227219289456
},
"communicator.exchange": {
"total": 1047.7815574427973,
"count": 228292,
"is_parallel": true,
"self": 1047.7815574427973
},
"steps_from_proto": {
"total": 86.66945563914942,
"count": 228292,
"is_parallel": true,
"self": 32.2989156241797,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.37054001496972,
"count": 456584,
"is_parallel": true,
"self": 54.37054001496972
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 487.9894178119371,
"count": 228293,
"self": 6.314179726785824,
"children": {
"process_trajectory": {
"total": 169.825385051151,
"count": 228293,
"self": 168.57064478315215,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2547402679988409,
"count": 10,
"self": 1.2547402679988409
}
}
},
"_update_policy": {
"total": 311.84985303400026,
"count": 95,
"self": 248.47268876903036,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.377164264969906,
"count": 2850,
"self": 63.377164264969906
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.85000042419415e-07,
"count": 1,
"self": 9.85000042419415e-07
},
"TrainerController._save_models": {
"total": 0.1372892219997084,
"count": 1,
"self": 0.0034738089998427313,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13381541299986566,
"count": 1,
"self": 0.13381541299986566
}
}
}
}
}
}
}