OliP's picture
First version
28db7c4
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5385637879371643,
"min": 0.5113246440887451,
"max": 1.4174872636795044,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 16156.9140625,
"min": 15339.7392578125,
"max": 43000.89453125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989931.0,
"min": 29953.0,
"max": 989931.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989931.0,
"min": 29953.0,
"max": 989931.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.16724006831645966,
"min": -0.09951090812683105,
"max": 0.20000457763671875,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 42.311737060546875,
"min": -23.982128143310547,
"max": 51.201171875,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.012174218893051147,
"min": 0.006481611169874668,
"max": 0.23368480801582336,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 3.0800774097442627,
"min": 1.5815131664276123,
"max": 56.31803894042969,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0681850351753556,
"min": 0.06408620212755685,
"max": 0.07357088800526879,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9545904924549783,
"min": 0.4964158452342094,
"max": 1.08691040763983,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.008775231971889124,
"min": 0.0003640050960379645,
"max": 0.01031244774416647,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.12285324760644774,
"min": 0.004732066248493538,
"max": 0.1443742684183306,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.669918871964286e-06,
"min": 7.669918871964286e-06,
"max": 0.00029523835873007144,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010737886420750001,
"min": 0.00010737886420750001,
"max": 0.003369307976897399,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10255660714285712,
"min": 0.10255660714285712,
"max": 0.1984127857142857,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4357924999999998,
"min": 1.3888894999999999,
"max": 2.4852443,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002654050535714287,
"min": 0.0002654050535714287,
"max": 0.009841437292857141,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0037156707500000017,
"min": 0.0037156707500000017,
"max": 0.11232794974,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01122946385294199,
"min": 0.01122946385294199,
"max": 0.47513267397880554,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.157212495803833,
"min": 0.157212495803833,
"max": 3.3259286880493164,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 692.1304347826087,
"min": 622.14,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31838.0,
"min": 16624.0,
"max": 32284.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.6990130061040754,
"min": -1.0000000521540642,
"max": 0.8577199664711952,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 32.15459828078747,
"min": -32.000001668930054,
"max": 42.88599832355976,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.6990130061040754,
"min": -1.0000000521540642,
"max": 0.8577199664711952,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 32.15459828078747,
"min": -32.000001668930054,
"max": 42.88599832355976,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.07964074951925558,
"min": 0.0751442163970205,
"max": 9.687888451084932,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.6634744778857566,
"min": 3.361559604963986,
"max": 164.69410366844386,
"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": "1674489480",
"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": "1.21.6",
"end_time_seconds": "1674491421"
},
"total": 1940.583170379,
"count": 1,
"self": 0.3822982990000128,
"children": {
"run_training.setup": {
"total": 0.09620766400007597,
"count": 1,
"self": 0.09620766400007597
},
"TrainerController.start_learning": {
"total": 1940.1046644159999,
"count": 1,
"self": 1.1639642900115632,
"children": {
"TrainerController._reset_env": {
"total": 5.950507628999958,
"count": 1,
"self": 5.950507628999958
},
"TrainerController.advance": {
"total": 1932.9074431449883,
"count": 63279,
"self": 1.252127072912117,
"children": {
"env_step": {
"total": 1301.3217328180785,
"count": 63279,
"self": 1200.3769511459805,
"children": {
"SubprocessEnvManager._take_step": {
"total": 100.21476532803945,
"count": 63279,
"self": 4.234055122076597,
"children": {
"TorchPolicy.evaluate": {
"total": 95.98071020596285,
"count": 62563,
"self": 32.558919955948795,
"children": {
"TorchPolicy.sample_actions": {
"total": 63.421790250014055,
"count": 62563,
"self": 63.421790250014055
}
}
}
}
},
"workers": {
"total": 0.7300163440586402,
"count": 63279,
"self": 0.0,
"children": {
"worker_root": {
"total": 1935.791325389037,
"count": 63279,
"is_parallel": true,
"self": 831.8706516899906,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019450629999937519,
"count": 1,
"is_parallel": true,
"self": 0.000718956000127946,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012261069998658058,
"count": 8,
"is_parallel": true,
"self": 0.0012261069998658058
}
}
},
"UnityEnvironment.step": {
"total": 0.05398851099994317,
"count": 1,
"is_parallel": true,
"self": 0.0004850159998568415,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000433616999998776,
"count": 1,
"is_parallel": true,
"self": 0.000433616999998776
},
"communicator.exchange": {
"total": 0.05075163299989072,
"count": 1,
"is_parallel": true,
"self": 0.05075163299989072
},
"steps_from_proto": {
"total": 0.002318245000196839,
"count": 1,
"is_parallel": true,
"self": 0.0005072779999863997,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018109670002104394,
"count": 8,
"is_parallel": true,
"self": 0.0018109670002104394
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1103.9206736990463,
"count": 63278,
"is_parallel": true,
"self": 27.102068651944137,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.033081136071814,
"count": 63278,
"is_parallel": true,
"self": 23.033081136071814
},
"communicator.exchange": {
"total": 953.5284639340116,
"count": 63278,
"is_parallel": true,
"self": 953.5284639340116
},
"steps_from_proto": {
"total": 100.2570599770188,
"count": 63278,
"is_parallel": true,
"self": 21.786888932146667,
"children": {
"_process_rank_one_or_two_observation": {
"total": 78.47017104487213,
"count": 506224,
"is_parallel": true,
"self": 78.47017104487213
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 630.3335832539976,
"count": 63279,
"self": 2.0959098319654004,
"children": {
"process_trajectory": {
"total": 143.51248935402418,
"count": 63279,
"self": 143.33035102102394,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18213833300023907,
"count": 2,
"self": 0.18213833300023907
}
}
},
"_update_policy": {
"total": 484.72518406800805,
"count": 448,
"self": 183.23470652403626,
"children": {
"TorchPPOOptimizer.update": {
"total": 301.4904775439718,
"count": 22797,
"self": 301.4904775439718
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.569998837832827e-07,
"count": 1,
"self": 9.569998837832827e-07
},
"TrainerController._save_models": {
"total": 0.08274839500018061,
"count": 1,
"self": 0.001323560000400903,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0814248349997797,
"count": 1,
"self": 0.0814248349997797
}
}
}
}
}
}
}