{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5058273077011108, "min": 0.5058273077011108, "max": 1.3987865447998047, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15182.912109375, "min": 15106.75390625, "max": 42433.58984375, "count": 33 }, "Pyramids.Step.mean": { "value": 989929.0, "min": 29952.0, "max": 989929.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989929.0, "min": 29952.0, "max": 989929.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6168438196182251, "min": -0.08122702687978745, "max": 0.6168438196182251, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 173.949951171875, "min": -19.656940460205078, "max": 173.949951171875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.019638346508145332, "min": -0.019638346508145332, "max": 0.25809887051582336, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -5.538013458251953, "min": -5.538013458251953, "max": 61.9437255859375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07186779868719721, "min": 0.06388730737488293, "max": 0.07220879639943334, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.006149181620761, "min": 0.4976628560200869, "max": 1.0677849066560157, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014940973777681521, "min": 0.000823871044255936, "max": 0.016928747193918268, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2091736328875413, "min": 0.007625903233992145, "max": 0.253931207908774, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.3395975534999975e-06, "min": 7.3395975534999975e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010275436574899996, "min": 0.00010275436574899996, "max": 0.0035075363308213, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024465, "min": 0.1024465, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.434251, "min": 1.3691136000000002, "max": 2.5691787, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002544053499999999, "min": 0.0002544053499999999, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035616748999999985, "min": 0.0035616748999999985, "max": 0.11694095213000004, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009017963893711567, "min": 0.009017963893711567, "max": 0.46099159121513367, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1262514889240265, "min": 0.1262514889240265, "max": 3.2269411087036133, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 312.1914893617021, "min": 302.68, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29346.0, "min": 15984.0, "max": 32600.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.666529764044792, "min": -1.0000000521540642, "max": 1.6992323023803306, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 156.65379782021046, "min": -32.000001668930054, "max": 168.22399793565273, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.666529764044792, "min": -1.0000000521540642, "max": 1.6992323023803306, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 156.65379782021046, "min": -32.000001668930054, "max": 168.22399793565273, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.029204576949036602, "min": 0.029204576949036602, "max": 8.814843412488699, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.7452302332094405, "min": 2.7398777788621373, "max": 141.03749459981918, "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": "1689721713", "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": "1689724120" }, "total": 2406.9827441939997, "count": 1, "self": 0.47909773599985783, "children": { "run_training.setup": { "total": 0.041664409999839336, "count": 1, "self": 0.041664409999839336 }, "TrainerController.start_learning": { "total": 2406.461982048, "count": 1, "self": 1.4672575149024851, "children": { "TrainerController._reset_env": { "total": 4.111460921999878, "count": 1, "self": 4.111460921999878 }, "TrainerController.advance": { "total": 2400.7782376250975, "count": 63858, "self": 1.512160880105057, "children": { "env_step": { "total": 1706.7683907799974, "count": 63858, "self": 1586.265506789116, "children": { "SubprocessEnvManager._take_step": { "total": 119.64083582196372, "count": 63858, "self": 5.115557743981526, "children": { "TorchPolicy.evaluate": { "total": 114.5252780779822, "count": 62559, "self": 114.5252780779822 } } }, "workers": { "total": 0.8620481689176813, "count": 63858, "self": 0.0, "children": { "worker_root": { "total": 2400.6435004579494, "count": 63858, "is_parallel": true, "self": 938.967263501959, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002155462000018815, "count": 1, "is_parallel": true, "self": 0.0006303840002601646, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015250779997586505, "count": 8, "is_parallel": true, "self": 0.0015250779997586505 } } }, "UnityEnvironment.step": { "total": 0.053580919000069116, "count": 1, "is_parallel": true, "self": 0.0005619740002202889, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004973469999640656, "count": 1, "is_parallel": true, "self": 0.0004973469999640656 }, "communicator.exchange": { "total": 0.05053480099991248, "count": 1, "is_parallel": true, "self": 0.05053480099991248 }, "steps_from_proto": { "total": 0.0019867969999722845, "count": 1, "is_parallel": true, "self": 0.0003928549999727693, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015939419999995152, "count": 8, "is_parallel": true, "self": 0.0015939419999995152 } } } } } } }, "UnityEnvironment.step": { "total": 1461.6762369559904, "count": 63857, "is_parallel": true, "self": 35.34888076200582, "children": { "UnityEnvironment._generate_step_input": { "total": 25.098713445080648, "count": 63857, "is_parallel": true, "self": 25.098713445080648 }, "communicator.exchange": { "total": 1285.4651235589042, "count": 63857, "is_parallel": true, "self": 1285.4651235589042 }, "steps_from_proto": { "total": 115.76351918999967, "count": 63857, "is_parallel": true, "self": 22.71590084413492, "children": { "_process_rank_one_or_two_observation": { "total": 93.04761834586475, "count": 510856, "is_parallel": true, "self": 93.04761834586475 } } } } } } } } } } }, "trainer_advance": { "total": 692.4976859649951, "count": 63858, "self": 2.744200517986883, "children": { "process_trajectory": { "total": 121.81872224700919, "count": 63858, "self": 121.53939231100912, "children": { "RLTrainer._checkpoint": { "total": 0.2793299360000674, "count": 2, "self": 0.2793299360000674 } } }, "_update_policy": { "total": 567.934763199999, "count": 451, "self": 367.22143492799, "children": { "TorchPPOOptimizer.update": { "total": 200.713328272009, "count": 22851, "self": 200.713328272009 } } } } } } }, "trainer_threads": { "total": 9.73000169324223e-07, "count": 1, "self": 9.73000169324223e-07 }, "TrainerController._save_models": { "total": 0.10502501300015865, "count": 1, "self": 0.001445975000024191, "children": { "RLTrainer._checkpoint": { "total": 0.10357903800013446, "count": 1, "self": 0.10357903800013446 } } } } } } }