ppo-Pyramids / run_logs /timers.json
dor88's picture
first try - vanilla
cd1891d
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.22839243710041046,
"min": 0.18432044982910156,
"max": 1.4437413215637207,
"count": 50
},
"Pyramids.Policy.Entropy.sum": {
"value": 6829.84765625,
"min": 5576.79931640625,
"max": 43797.3359375,
"count": 50
},
"Pyramids.Step.mean": {
"value": 1499991.0,
"min": 29952.0,
"max": 1499991.0,
"count": 50
},
"Pyramids.Step.sum": {
"value": 1499991.0,
"min": 29952.0,
"max": 1499991.0,
"count": 50
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.7333989143371582,
"min": -0.20012448728084564,
"max": 0.7885206341743469,
"count": 50
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 209.75209045410156,
"min": -47.42950439453125,
"max": 233.7647247314453,
"count": 50
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.01940484158694744,
"min": -0.0008903242414817214,
"max": 0.17391201853752136,
"count": 50
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 5.5497846603393555,
"min": -0.25285208225250244,
"max": 41.73888397216797,
"count": 50
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0686342873290088,
"min": 0.06503119869254684,
"max": 0.07339837436544865,
"count": 50
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.960880022606123,
"min": 0.493578841443854,
"max": 1.077253993203996,
"count": 50
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015275912309994503,
"min": 0.0007307594856079991,
"max": 0.016623892740989545,
"count": 50
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.21386277233992304,
"min": 0.006453380710850959,
"max": 0.23451116993480048,
"count": 50
},
"Pyramids.Policy.LearningRate.mean": {
"value": 2.845927622819046e-06,
"min": 2.845927622819046e-06,
"max": 0.00029676708679192377,
"count": 50
},
"Pyramids.Policy.LearningRate.sum": {
"value": 3.984298671946664e-05,
"min": 3.984298671946664e-05,
"max": 0.003654434781855133,
"count": 50
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10094860952380955,
"min": 0.10094860952380955,
"max": 0.19892236190476195,
"count": 50
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4132805333333336,
"min": 1.3794090666666667,
"max": 2.6181448666666673,
"count": 50
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00010476609142857136,
"min": 0.00010476609142857136,
"max": 0.009892343954285714,
"count": 50
},
"Pyramids.Policy.Beta.sum": {
"value": 0.001466725279999999,
"min": 0.001466725279999999,
"max": 0.12183267218000002,
"count": 50
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.006505767814815044,
"min": 0.006505767814815044,
"max": 0.3925413489341736,
"count": 50
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.09108074754476547,
"min": 0.09108074754476547,
"max": 2.7477893829345703,
"count": 50
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 259.1551724137931,
"min": 232.59055118110237,
"max": 999.0,
"count": 50
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30062.0,
"min": 15984.0,
"max": 32572.0,
"count": 50
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6534365122085033,
"min": -1.0000000521540642,
"max": 1.763793635581221,
"count": 50
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 190.14519890397787,
"min": -32.000001668930054,
"max": 222.23799808323383,
"count": 50
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6534365122085033,
"min": -1.0000000521540642,
"max": 1.763793635581221,
"count": 50
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 190.14519890397787,
"min": -32.000001668930054,
"max": 222.23799808323383,
"count": 50
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.017669609836657007,
"min": 0.016486777902981784,
"max": 9.033822645433247,
"count": 50
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.0320051312155556,
"min": 1.9262538901530206,
"max": 144.54116232693195,
"count": 50
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1677570955",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.22.4",
"end_time_seconds": "1677574510"
},
"total": 3554.827272875,
"count": 1,
"self": 0.6322481019997213,
"children": {
"run_training.setup": {
"total": 0.11004293799999232,
"count": 1,
"self": 0.11004293799999232
},
"TrainerController.start_learning": {
"total": 3554.0849818350002,
"count": 1,
"self": 1.919751412000096,
"children": {
"TrainerController._reset_env": {
"total": 8.777968566999903,
"count": 1,
"self": 8.777968566999903
},
"TrainerController.advance": {
"total": 3543.3016911280006,
"count": 96831,
"self": 2.0519168289179106,
"children": {
"env_step": {
"total": 2447.7628147260934,
"count": 96831,
"self": 2282.4525107970594,
"children": {
"SubprocessEnvManager._take_step": {
"total": 164.11128812598827,
"count": 96831,
"self": 6.805523776924474,
"children": {
"TorchPolicy.evaluate": {
"total": 157.3057643490638,
"count": 93814,
"self": 53.519098218008935,
"children": {
"TorchPolicy.sample_actions": {
"total": 103.78666613105486,
"count": 93814,
"self": 103.78666613105486
}
}
}
}
},
"workers": {
"total": 1.1990158030456541,
"count": 96831,
"self": 0.0,
"children": {
"worker_root": {
"total": 3546.662018120017,
"count": 96831,
"is_parallel": true,
"self": 1435.8353681010099,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007038326999918354,
"count": 1,
"is_parallel": true,
"self": 0.003692495000109375,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003345831999808979,
"count": 8,
"is_parallel": true,
"self": 0.003345831999808979
}
}
},
"UnityEnvironment.step": {
"total": 0.056729058999962945,
"count": 1,
"is_parallel": true,
"self": 0.0005216759999484566,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004687760000479102,
"count": 1,
"is_parallel": true,
"self": 0.0004687760000479102
},
"communicator.exchange": {
"total": 0.05418442200004847,
"count": 1,
"is_parallel": true,
"self": 0.05418442200004847
},
"steps_from_proto": {
"total": 0.0015541849999181068,
"count": 1,
"is_parallel": true,
"self": 0.0003867970000328569,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011673879998852499,
"count": 8,
"is_parallel": true,
"self": 0.0011673879998852499
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 2110.826650019007,
"count": 96830,
"is_parallel": true,
"self": 47.30325642605021,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 34.00615636402233,
"count": 96830,
"is_parallel": true,
"self": 34.00615636402233
},
"communicator.exchange": {
"total": 1893.460909448027,
"count": 96830,
"is_parallel": true,
"self": 1893.460909448027
},
"steps_from_proto": {
"total": 136.0563277809075,
"count": 96830,
"is_parallel": true,
"self": 32.26792811801283,
"children": {
"_process_rank_one_or_two_observation": {
"total": 103.78839966289468,
"count": 774640,
"is_parallel": true,
"self": 103.78839966289468
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1093.4869595729892,
"count": 96831,
"self": 3.7648673500184486,
"children": {
"process_trajectory": {
"total": 240.6336452199729,
"count": 96831,
"self": 240.3377468949733,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2958983249995981,
"count": 3,
"self": 0.2958983249995981
}
}
},
"_update_policy": {
"total": 849.088447002998,
"count": 682,
"self": 327.5600163769476,
"children": {
"TorchPPOOptimizer.update": {
"total": 521.5284306260504,
"count": 34296,
"self": 521.5284306260504
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.65000401972793e-07,
"count": 1,
"self": 8.65000401972793e-07
},
"TrainerController._save_models": {
"total": 0.08556986299936398,
"count": 1,
"self": 0.0013951399996585678,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08417472299970541,
"count": 1,
"self": 0.08417472299970541
}
}
}
}
}
}
}