{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.48065537214279175, "min": 0.47820350527763367, "max": 1.4306094646453857, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14604.232421875, "min": 14162.474609375, "max": 43398.96875, "count": 33 }, "Pyramids.Step.mean": { "value": 989958.0, "min": 29952.0, "max": 989958.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989958.0, "min": 29952.0, "max": 989958.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5209935307502747, "min": -0.10041186958551407, "max": 0.5209935307502747, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 142.23123168945312, "min": -24.199260711669922, "max": 142.23123168945312, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.004702025558799505, "min": -0.0007163012051023543, "max": 0.6409671306610107, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.2836530208587646, "min": -0.18623831868171692, "max": 151.90921020507812, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07074842885638298, "min": 0.06475211228377162, "max": 0.0742031078177399, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9904780039893618, "min": 0.48985153036934703, "max": 1.0752301057606624, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015018648545568187, "min": 0.0002570170939261054, "max": 0.015018648545568187, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21026107963795462, "min": 0.00334122222103937, "max": 0.21843737323212606, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.302761851492858e-06, "min": 7.302761851492858e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010223866592090001, "min": 0.00010223866592090001, "max": 0.0035093216302262, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243422142857146, "min": 0.10243422142857146, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340791000000004, "min": 1.3886848, "max": 2.5697738000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025317872071428573, "min": 0.00025317872071428573, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035445020900000002, "min": 0.0035445020900000002, "max": 0.11700040262, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007329114712774754, "min": 0.007329114712774754, "max": 0.499494731426239, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1026076078414917, "min": 0.1026076078414917, "max": 3.4964630603790283, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 359.4698795180723, "min": 351.3614457831325, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29836.0, "min": 15984.0, "max": 33237.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5449833108910493, "min": -1.0000000521540642, "max": 1.5617199820280074, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 129.77859811484814, "min": -30.99500161409378, "max": 129.77859811484814, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5449833108910493, "min": -1.0000000521540642, "max": 1.5617199820280074, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 129.77859811484814, "min": -30.99500161409378, "max": 129.77859811484814, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.027402377335030387, "min": 0.027402377335030387, "max": 11.319110445678234, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.3017996961425524, "min": 2.3017996961425524, "max": 181.10576713085175, "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": "1690480221", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "1690482478" }, "total": 2257.102949854, "count": 1, "self": 0.4910506410005837, "children": { "run_training.setup": { "total": 0.031254583999952956, "count": 1, "self": 0.031254583999952956 }, "TrainerController.start_learning": { "total": 2256.580644629, "count": 1, "self": 1.451305063961172, "children": { "TrainerController._reset_env": { "total": 4.018583252000099, "count": 1, "self": 4.018583252000099 }, "TrainerController.advance": { "total": 2251.0143673680386, "count": 63800, "self": 1.4311094790250536, "children": { "env_step": { "total": 1583.85648961903, "count": 63800, "self": 1468.7955659510467, "children": { "SubprocessEnvManager._take_step": { "total": 114.16366479894441, "count": 63800, "self": 5.001356700915949, "children": { "TorchPolicy.evaluate": { "total": 109.16230809802846, "count": 62575, "self": 109.16230809802846 } } }, "workers": { "total": 0.8972588690389784, "count": 63800, "self": 0.0, "children": { "worker_root": { "total": 2251.333984953061, "count": 63800, "is_parallel": true, "self": 903.8794251460588, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001867679000042699, "count": 1, "is_parallel": true, "self": 0.0006061480000880692, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012615309999546298, "count": 8, "is_parallel": true, "self": 0.0012615309999546298 } } }, "UnityEnvironment.step": { "total": 0.05252024000014899, "count": 1, "is_parallel": true, "self": 0.0006253359999845998, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005526899999495072, "count": 1, "is_parallel": true, "self": 0.0005526899999495072 }, "communicator.exchange": { "total": 0.049304133000077854, "count": 1, "is_parallel": true, "self": 0.049304133000077854 }, "steps_from_proto": { "total": 0.0020380810001370264, "count": 1, "is_parallel": true, "self": 0.0004078670003764273, "children": { "_process_rank_one_or_two_observation": { "total": 0.001630213999760599, "count": 8, "is_parallel": true, "self": 0.001630213999760599 } } } } } } }, "UnityEnvironment.step": { "total": 1347.4545598070024, "count": 63799, "is_parallel": true, "self": 35.06721338000489, "children": { "UnityEnvironment._generate_step_input": { "total": 24.71287016897736, "count": 63799, "is_parallel": true, "self": 24.71287016897736 }, "communicator.exchange": { "total": 1179.1108184260231, "count": 63799, "is_parallel": true, "self": 1179.1108184260231 }, "steps_from_proto": { "total": 108.56365783199703, "count": 63799, "is_parallel": true, "self": 22.411033658054976, "children": { "_process_rank_one_or_two_observation": { "total": 86.15262417394206, "count": 510392, "is_parallel": true, "self": 86.15262417394206 } } } } } } } } } } }, "trainer_advance": { "total": 665.7267682699835, "count": 63800, "self": 2.712156119008341, "children": { "process_trajectory": { "total": 117.29094561497504, "count": 63800, "self": 117.07716145497534, "children": { "RLTrainer._checkpoint": { "total": 0.21378415999970457, "count": 2, "self": 0.21378415999970457 } } }, "_update_policy": { "total": 545.7236665360001, "count": 452, "self": 358.03801559404496, "children": { "TorchPPOOptimizer.update": { "total": 187.68565094195515, "count": 22746, "self": 187.68565094195515 } } } } } } }, "trainer_threads": { "total": 1.711000095383497e-06, "count": 1, "self": 1.711000095383497e-06 }, "TrainerController._save_models": { "total": 0.09638723399984883, "count": 1, "self": 0.0015832799999770941, "children": { "RLTrainer._checkpoint": { "total": 0.09480395399987174, "count": 1, "self": 0.09480395399987174 } } } } } } }