ppo-Pyramids / run_logs /timers.json
lacknerm's picture
First Push
36dae6e verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.8421513438224792,
"min": 0.8421513438224792,
"max": 1.4279040098190308,
"count": 3
},
"Pyramids.Policy.Entropy.sum": {
"value": 25453.181640625,
"min": 25453.181640625,
"max": 43316.89453125,
"count": 3
},
"Pyramids.Step.mean": {
"value": 89901.0,
"min": 29952.0,
"max": 89901.0,
"count": 3
},
"Pyramids.Step.sum": {
"value": 89901.0,
"min": 29952.0,
"max": 89901.0,
"count": 3
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.05049468204379082,
"min": -0.1536472886800766,
"max": -0.05049468204379082,
"count": 3
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -12.169218063354492,
"min": -36.414405822753906,
"max": -12.169218063354492,
"count": 3
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.1693786084651947,
"min": 0.1693786084651947,
"max": 0.2747419476509094,
"count": 3
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 40.82024383544922,
"min": 40.82024383544922,
"max": 66.487548828125,
"count": 3
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06846776156642985,
"min": 0.06846776156642985,
"max": 0.07196624864031591,
"count": 3
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.8216131387971582,
"min": 0.49820701944019213,
"max": 0.8216131387971582,
"count": 3
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.002095540043834882,
"min": 0.002095540043834882,
"max": 0.006562098728055988,
"count": 3
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.02514648052601858,
"min": 0.0217551727780026,
"max": 0.045934691096391915,
"count": 3
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.848182383941666e-05,
"min": 7.848182383941666e-05,
"max": 0.0002515063018788571,
"count": 3
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.000941781886073,
"min": 0.000941781886073,
"max": 0.0017605441131519997,
"count": 3
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.12616058333333333,
"min": 0.12616058333333333,
"max": 0.1838354285714286,
"count": 3
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.513927,
"min": 1.2868480000000002,
"max": 1.513927,
"count": 3
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0026234422750000003,
"min": 0.0026234422750000003,
"max": 0.008385159314285713,
"count": 3
},
"Pyramids.Policy.Beta.sum": {
"value": 0.031481307300000004,
"min": 0.031481307300000004,
"max": 0.058696115199999996,
"count": 3
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.11525529623031616,
"min": 0.11525529623031616,
"max": 0.49059638381004333,
"count": 3
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 1.383063554763794,
"min": 1.383063554763794,
"max": 3.4341747760772705,
"count": 3
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 971.125,
"min": 962.0,
"max": 999.0,
"count": 3
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31076.0,
"min": 15984.0,
"max": 33670.0,
"count": 3
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -0.8470062969718128,
"min": -1.0000000521540642,
"max": -0.7914857677050999,
"count": 3
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -27.10420150309801,
"min": -27.702001869678497,
"max": -16.000000834465027,
"count": 3
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -0.8470062969718128,
"min": -1.0000000521540642,
"max": -0.7914857677050999,
"count": 3
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -27.10420150309801,
"min": -27.702001869678497,
"max": -16.000000834465027,
"count": 3
},
"Pyramids.Policy.RndReward.mean": {
"value": 1.2553130452288315,
"min": 1.2553130452288315,
"max": 10.210595269687474,
"count": 3
},
"Pyramids.Policy.RndReward.sum": {
"value": 40.17001744732261,
"min": 40.17001744732261,
"max": 163.36952431499958,
"count": 3
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 3
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 3
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1713439258",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1713439556"
},
"total": 298.24101804899993,
"count": 1,
"self": 0.6387142049999284,
"children": {
"run_training.setup": {
"total": 0.06710730600002535,
"count": 1,
"self": 0.06710730600002535
},
"TrainerController.start_learning": {
"total": 297.535196538,
"count": 1,
"self": 0.20759824399340232,
"children": {
"TrainerController._reset_env": {
"total": 3.136738426000022,
"count": 1,
"self": 3.136738426000022
},
"TrainerController.advance": {
"total": 294.03977961400653,
"count": 6305,
"self": 0.23763696300426318,
"children": {
"env_step": {
"total": 190.7710552949979,
"count": 6305,
"self": 175.57253945799755,
"children": {
"SubprocessEnvManager._take_step": {
"total": 15.069660322000175,
"count": 6305,
"self": 0.6626234760024658,
"children": {
"TorchPolicy.evaluate": {
"total": 14.407036845997709,
"count": 6297,
"self": 14.407036845997709
}
}
},
"workers": {
"total": 0.12885551500016845,
"count": 6305,
"self": 0.0,
"children": {
"worker_root": {
"total": 296.8999725839998,
"count": 6305,
"is_parallel": true,
"self": 138.3617462400012,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007409946999985095,
"count": 1,
"is_parallel": true,
"self": 0.00333795099999179,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.004071995999993305,
"count": 8,
"is_parallel": true,
"self": 0.004071995999993305
}
}
},
"UnityEnvironment.step": {
"total": 0.057863819000033345,
"count": 1,
"is_parallel": true,
"self": 0.0007494500000007065,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005209889999946427,
"count": 1,
"is_parallel": true,
"self": 0.0005209889999946427
},
"communicator.exchange": {
"total": 0.05462544700003491,
"count": 1,
"is_parallel": true,
"self": 0.05462544700003491
},
"steps_from_proto": {
"total": 0.001967933000003086,
"count": 1,
"is_parallel": true,
"self": 0.0004303680000816712,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015375649999214147,
"count": 8,
"is_parallel": true,
"self": 0.0015375649999214147
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 158.5382263439986,
"count": 6304,
"is_parallel": true,
"self": 4.9335431810033015,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.6564381849967162,
"count": 6304,
"is_parallel": true,
"self": 2.6564381849967162
},
"communicator.exchange": {
"total": 138.00420611499914,
"count": 6304,
"is_parallel": true,
"self": 138.00420611499914
},
"steps_from_proto": {
"total": 12.944038862999435,
"count": 6304,
"is_parallel": true,
"self": 2.7626011990102484,
"children": {
"_process_rank_one_or_two_observation": {
"total": 10.181437663989186,
"count": 50432,
"is_parallel": true,
"self": 10.181437663989186
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 103.03108735600438,
"count": 6305,
"self": 0.3195928790049152,
"children": {
"process_trajectory": {
"total": 15.509347857999614,
"count": 6305,
"self": 15.509347857999614
},
"_update_policy": {
"total": 87.20214661899985,
"count": 33,
"self": 35.90319550999601,
"children": {
"TorchPPOOptimizer.update": {
"total": 51.29895110900384,
"count": 2307,
"self": 51.29895110900384
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0930000371445203e-06,
"count": 1,
"self": 1.0930000371445203e-06
},
"TrainerController._save_models": {
"total": 0.1510791609999842,
"count": 1,
"self": 0.0028678099999979167,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14821135099998628,
"count": 1,
"self": 0.14821135099998628
}
}
}
}
}
}
}