ppo-Pyramids / run_logs /timers.json
Orion181's picture
First Push
80fe6c4 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.17222033441066742,
"min": 0.16300146281719208,
"max": 1.3919081687927246,
"count": 100
},
"Pyramids.Policy.Entropy.sum": {
"value": 5133.5439453125,
"min": 4890.0439453125,
"max": 42224.92578125,
"count": 100
},
"Pyramids.Step.mean": {
"value": 2999964.0,
"min": 29912.0,
"max": 2999964.0,
"count": 100
},
"Pyramids.Step.sum": {
"value": 2999964.0,
"min": 29912.0,
"max": 2999964.0,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.7999983429908752,
"min": -0.18867026269435883,
"max": 0.8709744811058044,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 240.79949951171875,
"min": -44.71485137939453,
"max": 268.2601318359375,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.009617633186280727,
"min": -0.0264639463275671,
"max": 0.306855708360672,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 2.8949074745178223,
"min": -7.56868839263916,
"max": 74.11662292480469,
"count": 100
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06990596332421996,
"min": 0.06352391739316214,
"max": 0.07383776822662848,
"count": 100
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9786834865390794,
"min": 0.5159899540164076,
"max": 1.1059900190619587,
"count": 100
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015043337423651276,
"min": 0.0002591578526321348,
"max": 0.016716598584372105,
"count": 100
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.21060672393111787,
"min": 0.003628209936849887,
"max": 0.24529163568513462,
"count": 100
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.4658066542880948e-06,
"min": 1.4658066542880948e-06,
"max": 0.00029841154338662855,
"count": 100
},
"Pyramids.Policy.LearningRate.sum": {
"value": 2.0521293160033327e-05,
"min": 2.0521293160033327e-05,
"max": 0.003969210876929733,
"count": 100
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10048856904761905,
"min": 0.10048856904761905,
"max": 0.1994705142857143,
"count": 100
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4068399666666667,
"min": 1.3962936000000001,
"max": 2.7230702666666664,
"count": 100
},
"Pyramids.Policy.Beta.mean": {
"value": 5.880804785714284e-05,
"min": 5.880804785714284e-05,
"max": 0.009947104377142857,
"count": 100
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0008233126699999998,
"min": 0.0008233126699999998,
"max": 0.13231471964,
"count": 100
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.0063171968795359135,
"min": 0.005784609355032444,
"max": 0.5587612390518188,
"count": 100
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.08844075351953506,
"min": 0.08098453283309937,
"max": 3.9113287925720215,
"count": 100
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 235.56923076923076,
"min": 210.88888888888889,
"max": 999.0,
"count": 100
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30624.0,
"min": 16711.0,
"max": 33355.0,
"count": 100
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7644307504479702,
"min": -0.9998800526062648,
"max": 1.7913036938066835,
"count": 100
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 229.37599755823612,
"min": -30.223601706326008,
"max": 252.66899845004082,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7644307504479702,
"min": -0.9998800526062648,
"max": 1.7913036938066835,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 229.37599755823612,
"min": -30.223601706326008,
"max": 252.66899845004082,
"count": 100
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.015391132933571219,
"min": 0.014547796560779076,
"max": 11.564084438716664,
"count": 100
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.0008472813642584,
"min": 1.7148659792728722,
"max": 196.5894354581833,
"count": 100
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1734841977",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]",
"command_line_arguments": "/home/vscode/.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": "2.5.1+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1734846506"
},
"total": 4529.367606932003,
"count": 1,
"self": 0.5317208790038421,
"children": {
"run_training.setup": {
"total": 0.06815523000113899,
"count": 1,
"self": 0.06815523000113899
},
"TrainerController.start_learning": {
"total": 4528.767730822998,
"count": 1,
"self": 3.931232677296066,
"children": {
"TrainerController._reset_env": {
"total": 6.023519793998275,
"count": 1,
"self": 6.023519793998275
},
"TrainerController.advance": {
"total": 4518.673316005708,
"count": 194660,
"self": 3.7683131038829742,
"children": {
"env_step": {
"total": 3126.5997235239265,
"count": 194660,
"self": 2905.7770212663927,
"children": {
"SubprocessEnvManager._take_step": {
"total": 218.4003914516179,
"count": 194660,
"self": 9.381705441035592,
"children": {
"TorchPolicy.evaluate": {
"total": 209.01868601058231,
"count": 187567,
"self": 209.01868601058231
}
}
},
"workers": {
"total": 2.422310805915913,
"count": 194660,
"self": 0.0,
"children": {
"worker_root": {
"total": 4521.23370574744,
"count": 194660,
"is_parallel": true,
"self": 1870.6284454281304,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002481530998920789,
"count": 1,
"is_parallel": true,
"self": 0.0010588369987090118,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014226940002117772,
"count": 8,
"is_parallel": true,
"self": 0.0014226940002117772
}
}
},
"UnityEnvironment.step": {
"total": 0.04007461999935913,
"count": 1,
"is_parallel": true,
"self": 0.00035246800325694494,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00028073700013919733,
"count": 1,
"is_parallel": true,
"self": 0.00028073700013919733
},
"communicator.exchange": {
"total": 0.03840638999827206,
"count": 1,
"is_parallel": true,
"self": 0.03840638999827206
},
"steps_from_proto": {
"total": 0.0010350249976909254,
"count": 1,
"is_parallel": true,
"self": 0.00027970600058324635,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000755318997107679,
"count": 8,
"is_parallel": true,
"self": 0.000755318997107679
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 2650.6052603193093,
"count": 194659,
"is_parallel": true,
"self": 51.17973695715773,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 33.695821456560225,
"count": 194659,
"is_parallel": true,
"self": 33.695821456560225
},
"communicator.exchange": {
"total": 2427.881117268411,
"count": 194659,
"is_parallel": true,
"self": 2427.881117268411
},
"steps_from_proto": {
"total": 137.84858463718047,
"count": 194659,
"is_parallel": true,
"self": 36.8439853127129,
"children": {
"_process_rank_one_or_two_observation": {
"total": 101.00459932446756,
"count": 1557272,
"is_parallel": true,
"self": 101.00459932446756
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1388.3052793778988,
"count": 194660,
"self": 7.110747145110508,
"children": {
"process_trajectory": {
"total": 277.76803155174275,
"count": 194660,
"self": 277.0563048157419,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7117267360008555,
"count": 6,
"self": 0.7117267360008555
}
}
},
"_update_policy": {
"total": 1103.4265006810456,
"count": 1396,
"self": 628.9710318170437,
"children": {
"TorchPPOOptimizer.update": {
"total": 474.4554688640019,
"count": 68397,
"self": 474.4554688640019
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0699950507842004e-06,
"count": 1,
"self": 1.0699950507842004e-06
},
"TrainerController._save_models": {
"total": 0.1396612759999698,
"count": 1,
"self": 0.027926337003009394,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11173493899696041,
"count": 1,
"self": 0.11173493899696041
}
}
}
}
}
}
}