ppo-Pyramids / run_logs /timers.json
Ale902's picture
First push
54d1828 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.48974716663360596,
"min": 0.48974716663360596,
"max": 1.4595179557800293,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 14817.7900390625,
"min": 14684.7509765625,
"max": 44275.9375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989929.0,
"min": 29952.0,
"max": 989929.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989929.0,
"min": 29952.0,
"max": 989929.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.3984176814556122,
"min": -0.09861604124307632,
"max": 0.42762067914009094,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 105.5806884765625,
"min": -23.667850494384766,
"max": 114.60234069824219,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.013768329285085201,
"min": -0.006755257491022348,
"max": 0.5250219106674194,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 3.6486072540283203,
"min": -1.8104090690612793,
"max": 124.43019104003906,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07053188242556929,
"min": 0.06407194413384618,
"max": 0.07322397811749437,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9874463539579701,
"min": 0.49555167541457823,
"max": 1.0464055893466782,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.013485141418274577,
"min": 0.00015187269541539335,
"max": 0.013485141418274577,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.1887919798558441,
"min": 0.0016705996495693268,
"max": 0.19916713694450058,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.369404686421429e-06,
"min": 7.369404686421429e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001031716656099,
"min": 0.0001031716656099,
"max": 0.0031377722540759994,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10245643571428573,
"min": 0.10245643571428573,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4343901000000001,
"min": 1.3691136000000002,
"max": 2.4422172000000004,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025539792785714293,
"min": 0.00025539792785714293,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003575570990000001,
"min": 0.003575570990000001,
"max": 0.1046178076,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.008445421233773232,
"min": 0.008445421233773232,
"max": 0.4096454083919525,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.11823589354753494,
"min": 0.11823589354753494,
"max": 2.8675179481506348,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 448.6825396825397,
"min": 418.5466666666667,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28267.0,
"min": 15984.0,
"max": 33959.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.3290317329385923,
"min": -1.0000000521540642,
"max": 1.4480879773696265,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 83.72899917513132,
"min": -32.000001668930054,
"max": 108.60659830272198,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.3290317329385923,
"min": -1.0000000521540642,
"max": 1.4480879773696265,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 83.72899917513132,
"min": -32.000001668930054,
"max": 108.60659830272198,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.039770148093498034,
"min": 0.038921899204918495,
"max": 8.485421846620739,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.505519329890376,
"min": 2.505519329890376,
"max": 135.76674954593182,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1748418359",
"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/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1748420663"
},
"total": 2304.2094797000004,
"count": 1,
"self": 0.5903117740008383,
"children": {
"run_training.setup": {
"total": 0.020848865000061778,
"count": 1,
"self": 0.020848865000061778
},
"TrainerController.start_learning": {
"total": 2303.5983190609995,
"count": 1,
"self": 1.4519563550538805,
"children": {
"TrainerController._reset_env": {
"total": 2.3900518530003865,
"count": 1,
"self": 2.3900518530003865
},
"TrainerController.advance": {
"total": 2299.659507447946,
"count": 63567,
"self": 1.5767298960295193,
"children": {
"env_step": {
"total": 1597.5127455359616,
"count": 63567,
"self": 1433.694942671993,
"children": {
"SubprocessEnvManager._take_step": {
"total": 162.98906954105223,
"count": 63567,
"self": 5.050776837158537,
"children": {
"TorchPolicy.evaluate": {
"total": 157.9382927038937,
"count": 62554,
"self": 157.9382927038937
}
}
},
"workers": {
"total": 0.8287333229163778,
"count": 63567,
"self": 0.0,
"children": {
"worker_root": {
"total": 2298.2891218500886,
"count": 63567,
"is_parallel": true,
"self": 984.5906673582035,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0021399830002337694,
"count": 1,
"is_parallel": true,
"self": 0.0007667340009902546,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013732489992435148,
"count": 8,
"is_parallel": true,
"self": 0.0013732489992435148
}
}
},
"UnityEnvironment.step": {
"total": 0.05577754200021445,
"count": 1,
"is_parallel": true,
"self": 0.0006625780001741077,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005005140001230757,
"count": 1,
"is_parallel": true,
"self": 0.0005005140001230757
},
"communicator.exchange": {
"total": 0.05287063199966724,
"count": 1,
"is_parallel": true,
"self": 0.05287063199966724
},
"steps_from_proto": {
"total": 0.0017438180002500303,
"count": 1,
"is_parallel": true,
"self": 0.0003910460004590277,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013527719997910026,
"count": 8,
"is_parallel": true,
"self": 0.0013527719997910026
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1313.698454491885,
"count": 63566,
"is_parallel": true,
"self": 33.79692681390361,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.761384070077384,
"count": 63566,
"is_parallel": true,
"self": 24.761384070077384
},
"communicator.exchange": {
"total": 1151.3121130529257,
"count": 63566,
"is_parallel": true,
"self": 1151.3121130529257
},
"steps_from_proto": {
"total": 103.82803055497834,
"count": 63566,
"is_parallel": true,
"self": 21.484218510907795,
"children": {
"_process_rank_one_or_two_observation": {
"total": 82.34381204407055,
"count": 508528,
"is_parallel": true,
"self": 82.34381204407055
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 700.5700320159549,
"count": 63567,
"self": 2.7705837039784456,
"children": {
"process_trajectory": {
"total": 136.4722401949789,
"count": 63567,
"self": 136.25711346097887,
"children": {
"RLTrainer._checkpoint": {
"total": 0.21512673400002313,
"count": 2,
"self": 0.21512673400002313
}
}
},
"_update_policy": {
"total": 561.3272081169976,
"count": 438,
"self": 313.3467717239937,
"children": {
"TorchPPOOptimizer.update": {
"total": 247.98043639300386,
"count": 22860,
"self": 247.98043639300386
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0929998097708449e-06,
"count": 1,
"self": 1.0929998097708449e-06
},
"TrainerController._save_models": {
"total": 0.0968023119994541,
"count": 1,
"self": 0.0014668629992229398,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09533544900023116,
"count": 1,
"self": 0.09533544900023116
}
}
}
}
}
}
}