ppo-PyramidsRND / run_logs /timers.json
felixdae
First Push
f1d48b7
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4126274287700653,
"min": 0.3963058292865753,
"max": 1.354868769645691,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 12332.6083984375,
"min": 11889.1748046875,
"max": 41101.30078125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989952.0,
"min": 29897.0,
"max": 989952.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989952.0,
"min": 29897.0,
"max": 989952.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.4419672191143036,
"min": -0.10150694847106934,
"max": 0.4497647285461426,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 118.8891830444336,
"min": -24.260160446166992,
"max": 121.88623809814453,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.025846702978014946,
"min": -0.007232185918837786,
"max": 0.22827371954917908,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 6.952763080596924,
"min": -1.9382258653640747,
"max": 55.01396560668945,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06723806425274927,
"min": 0.06531849044769938,
"max": 0.07303848105989179,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9413328995384896,
"min": 0.4925040605778394,
"max": 1.056378443355332,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.016533326555439827,
"min": 0.0005828888133610975,
"max": 0.017040945123397325,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.23146657177615756,
"min": 0.007577554573694268,
"max": 0.24042923289522936,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.239911872442854e-06,
"min": 7.239911872442854e-06,
"max": 0.0002952352730168143,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010135876621419996,
"min": 0.00010135876621419996,
"max": 0.0035068817310394997,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10241327142857144,
"min": 0.10241327142857144,
"max": 0.19841175714285714,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4337858,
"min": 1.3888823,
"max": 2.5689604999999998,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025108581571428563,
"min": 0.00025108581571428563,
"max": 0.009841334538571429,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0035152014199999987,
"min": 0.0035152014199999987,
"max": 0.11691915395,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.014342555776238441,
"min": 0.014342555776238441,
"max": 0.5017131567001343,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.20079578459262848,
"min": 0.20079578459262848,
"max": 3.5119919776916504,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 378.42857142857144,
"min": 378.42857142857144,
"max": 995.4333333333333,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29139.0,
"min": 16696.0,
"max": 33035.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4396908809612323,
"min": -0.929931303486228,
"max": 1.4396908809612323,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 110.85619783401489,
"min": -29.757801711559296,
"max": 110.85619783401489,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4396908809612323,
"min": -0.929931303486228,
"max": 1.4396908809612323,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 110.85619783401489,
"min": -29.757801711559296,
"max": 110.85619783401489,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.056259193509067225,
"min": 0.056259193509067225,
"max": 9.49549793758813,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.3319579001981765,
"min": 4.3319579001981765,
"max": 161.42346493899822,
"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": "1686543557",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "0.31.0.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": "1686546559"
},
"total": 3001.8124513260004,
"count": 1,
"self": 0.4752591019996544,
"children": {
"run_training.setup": {
"total": 0.04265260900001522,
"count": 1,
"self": 0.04265260900001522
},
"TrainerController.start_learning": {
"total": 3001.2945396150008,
"count": 1,
"self": 1.8053911140127639,
"children": {
"TrainerController._reset_env": {
"total": 1.1172516010001345,
"count": 1,
"self": 1.1172516010001345
},
"TrainerController.advance": {
"total": 2998.268954010988,
"count": 63552,
"self": 1.5123713929110636,
"children": {
"env_step": {
"total": 1632.5528562070156,
"count": 63552,
"self": 1488.9462165991129,
"children": {
"SubprocessEnvManager._take_step": {
"total": 142.4155121598983,
"count": 63552,
"self": 5.13694984483368,
"children": {
"TorchPolicy.evaluate": {
"total": 137.27856231506462,
"count": 62563,
"self": 137.27856231506462
}
}
},
"workers": {
"total": 1.1911274480044085,
"count": 63552,
"self": 0.0,
"children": {
"worker_root": {
"total": 2996.2506527800433,
"count": 63552,
"is_parallel": true,
"self": 1640.9694131060064,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019612099999903876,
"count": 1,
"is_parallel": true,
"self": 0.0005870799998319853,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013741300001584023,
"count": 8,
"is_parallel": true,
"self": 0.0013741300001584023
}
}
},
"UnityEnvironment.step": {
"total": 0.045900809999920966,
"count": 1,
"is_parallel": true,
"self": 0.0005905390000862099,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005495509999491333,
"count": 1,
"is_parallel": true,
"self": 0.0005495509999491333
},
"communicator.exchange": {
"total": 0.04287340999985645,
"count": 1,
"is_parallel": true,
"self": 0.04287340999985645
},
"steps_from_proto": {
"total": 0.0018873100000291743,
"count": 1,
"is_parallel": true,
"self": 0.00032652000027155736,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001560789999757617,
"count": 8,
"is_parallel": true,
"self": 0.001560789999757617
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1355.281239674037,
"count": 63551,
"is_parallel": true,
"self": 37.22143707914984,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.94962952800165,
"count": 63551,
"is_parallel": true,
"self": 22.94962952800165
},
"communicator.exchange": {
"total": 1187.2338129289271,
"count": 63551,
"is_parallel": true,
"self": 1187.2338129289271
},
"steps_from_proto": {
"total": 107.87636013795827,
"count": 63551,
"is_parallel": true,
"self": 21.922771889661362,
"children": {
"_process_rank_one_or_two_observation": {
"total": 85.95358824829691,
"count": 508408,
"is_parallel": true,
"self": 85.95358824829691
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1364.2037264110616,
"count": 63552,
"self": 3.5763097540566378,
"children": {
"process_trajectory": {
"total": 141.96002783601466,
"count": 63552,
"self": 141.75653038801488,
"children": {
"RLTrainer._checkpoint": {
"total": 0.20349744799977998,
"count": 2,
"self": 0.20349744799977998
}
}
},
"_update_policy": {
"total": 1218.6673888209903,
"count": 448,
"self": 357.56789741790976,
"children": {
"TorchPPOOptimizer.update": {
"total": 861.0994914030805,
"count": 22797,
"self": 861.0994914030805
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.910001270123757e-07,
"count": 1,
"self": 8.910001270123757e-07
},
"TrainerController._save_models": {
"total": 0.10294199799955095,
"count": 1,
"self": 0.001390789999277331,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10155120800027362,
"count": 1,
"self": 0.10155120800027362
}
}
}
}
}
}
}