ppo-Pyramids / run_logs /timers.json
rohn132's picture
First Push
97b8073
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.2989126741886139,
"min": 0.2989126741886139,
"max": 1.4436542987823486,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 9072.59765625,
"min": 9072.59765625,
"max": 43794.6953125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989984.0,
"min": 29908.0,
"max": 989984.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989984.0,
"min": 29908.0,
"max": 989984.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5364909172058105,
"min": -0.09286700934171677,
"max": 0.5414549708366394,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 149.14447021484375,
"min": -22.292495727539062,
"max": 149.14447021484375,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.02987596206367016,
"min": 0.010084972716867924,
"max": 0.35073304176330566,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 8.305517196655273,
"min": 2.682602643966675,
"max": 83.12373352050781,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06786293758722466,
"min": 0.06556648364700167,
"max": 0.07418343837036649,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9500811262211452,
"min": 0.48269940523300914,
"max": 1.1127515755554973,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.013875093594140795,
"min": 0.00021738470543989483,
"max": 0.014047219173724963,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.19425131031797113,
"min": 0.0028260011707186327,
"max": 0.19666106843214948,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.618318889164287e-06,
"min": 7.618318889164287e-06,
"max": 0.0002952348015884,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010665646444830001,
"min": 0.00010665646444830001,
"max": 0.0036334417888527993,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10253940714285714,
"min": 0.10253940714285714,
"max": 0.1984116,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4355517,
"min": 1.3888812,
"max": 2.6111471999999996,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026368677357142866,
"min": 0.00026368677357142866,
"max": 0.00984131884,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003691614830000001,
"min": 0.003691614830000001,
"max": 0.12113360528000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.037940140813589096,
"min": 0.03662216663360596,
"max": 0.46993550658226013,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.5311619639396667,
"min": 0.5164991617202759,
"max": 3.289548635482788,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 339.83516483516485,
"min": 339.83516483516485,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30925.0,
"min": 16707.0,
"max": 32235.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5252222056190172,
"min": -0.9998500528745353,
"max": 1.6110124825499952,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 137.26999850571156,
"min": -31.99520169198513,
"max": 137.26999850571156,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5252222056190172,
"min": -0.9998500528745353,
"max": 1.6110124825499952,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 137.26999850571156,
"min": -31.99520169198513,
"max": 137.26999850571156,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.13117907410293508,
"min": 0.13117907410293508,
"max": 8.846885418190675,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 11.806116669264156,
"min": 10.511265887238551,
"max": 150.39705210924149,
"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": "1692931909",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1692934229"
},
"total": 2319.4423249520005,
"count": 1,
"self": 0.8995214400001714,
"children": {
"run_training.setup": {
"total": 0.06624013300006482,
"count": 1,
"self": 0.06624013300006482
},
"TrainerController.start_learning": {
"total": 2318.4765633790003,
"count": 1,
"self": 1.318920739027817,
"children": {
"TrainerController._reset_env": {
"total": 4.628697011000213,
"count": 1,
"self": 4.628697011000213
},
"TrainerController.advance": {
"total": 2312.3785713739717,
"count": 63858,
"self": 1.3165784119637465,
"children": {
"env_step": {
"total": 1641.5370895119706,
"count": 63858,
"self": 1533.2071723269419,
"children": {
"SubprocessEnvManager._take_step": {
"total": 107.5227801869737,
"count": 63858,
"self": 4.622046196979227,
"children": {
"TorchPolicy.evaluate": {
"total": 102.90073398999448,
"count": 62581,
"self": 102.90073398999448
}
}
},
"workers": {
"total": 0.8071369980550571,
"count": 63858,
"self": 0.0,
"children": {
"worker_root": {
"total": 2313.4918685579737,
"count": 63858,
"is_parallel": true,
"self": 893.2963652889159,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0026867279998441518,
"count": 1,
"is_parallel": true,
"self": 0.0007060650000312307,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001980662999812921,
"count": 8,
"is_parallel": true,
"self": 0.001980662999812921
}
}
},
"UnityEnvironment.step": {
"total": 0.04964788500001305,
"count": 1,
"is_parallel": true,
"self": 0.0005966800001715455,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004931650000798982,
"count": 1,
"is_parallel": true,
"self": 0.0004931650000798982
},
"communicator.exchange": {
"total": 0.04659035299982861,
"count": 1,
"is_parallel": true,
"self": 0.04659035299982861
},
"steps_from_proto": {
"total": 0.001967686999932994,
"count": 1,
"is_parallel": true,
"self": 0.00037835300031474617,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015893339996182476,
"count": 8,
"is_parallel": true,
"self": 0.0015893339996182476
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1420.1955032690578,
"count": 63857,
"is_parallel": true,
"self": 33.96063004308894,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.049314843939783,
"count": 63857,
"is_parallel": true,
"self": 23.049314843939783
},
"communicator.exchange": {
"total": 1257.6007783799848,
"count": 63857,
"is_parallel": true,
"self": 1257.6007783799848
},
"steps_from_proto": {
"total": 105.58478000204423,
"count": 63857,
"is_parallel": true,
"self": 20.71381203996293,
"children": {
"_process_rank_one_or_two_observation": {
"total": 84.8709679620813,
"count": 510856,
"is_parallel": true,
"self": 84.8709679620813
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 669.5249034500375,
"count": 63858,
"self": 2.5453854340298676,
"children": {
"process_trajectory": {
"total": 111.69608916600646,
"count": 63858,
"self": 111.3661821020064,
"children": {
"RLTrainer._checkpoint": {
"total": 0.32990706400005365,
"count": 2,
"self": 0.32990706400005365
}
}
},
"_update_policy": {
"total": 555.2834288500012,
"count": 456,
"self": 360.9778594669906,
"children": {
"TorchPPOOptimizer.update": {
"total": 194.3055693830106,
"count": 22788,
"self": 194.3055693830106
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3389999367063865e-06,
"count": 1,
"self": 1.3389999367063865e-06
},
"TrainerController._save_models": {
"total": 0.1503729160003786,
"count": 1,
"self": 0.0018418620002194075,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1485310540001592,
"count": 1,
"self": 0.1485310540001592
}
}
}
}
}
}
}