{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3235231935977936, "min": 0.3235231935977936, "max": 1.470370888710022, "count": 35 }, "Pyramids.Policy.Entropy.sum": { "value": 9804.046875, "min": 9804.046875, "max": 44605.171875, "count": 35 }, "Pyramids.Step.mean": { "value": 1049950.0, "min": 29952.0, "max": 1049950.0, "count": 35 }, "Pyramids.Step.sum": { "value": 1049950.0, "min": 29952.0, "max": 1049950.0, "count": 35 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.47961777448654175, "min": -0.09587505459785461, "max": 0.6261691451072693, "count": 35 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 129.49679565429688, "min": -23.201763153076172, "max": 175.9535369873047, "count": 35 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.033712487667798996, "min": -0.0199218038469553, "max": 0.6391360759735107, "count": 35 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.102372169494629, "min": -5.418730735778809, "max": 151.47525024414062, "count": 35 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06894693976695028, "min": 0.0654920276919809, "max": 0.07365833486097, "count": 35 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.965257156737304, "min": 0.5131648753966398, "max": 1.0615146561176516, "count": 35 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015769388898098397, "min": 0.00024365157849089763, "max": 0.01656608596940281, "count": 35 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22077144457337755, "min": 0.0029238189418907714, "max": 0.23770943558067267, "count": 35 }, "Pyramids.Policy.LearningRate.mean": { "value": 4.3364250851700655e-06, "min": 4.3364250851700655e-06, "max": 0.00029538155255989107, "count": 35 }, "Pyramids.Policy.LearningRate.sum": { "value": 6.0709951192380914e-05, "min": 6.0709951192380914e-05, "max": 0.0034210868310663813, "count": 35 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10144544217687075, "min": 0.10144544217687075, "max": 0.19846051700680273, "count": 35 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4202361904761904, "min": 1.389223619047619, "max": 2.540362190476191, "count": 35 }, "Pyramids.Policy.Beta.mean": { "value": 0.00015439967346938768, "min": 0.00015439967346938768, "max": 0.009846205648979593, "count": 35 }, "Pyramids.Policy.Beta.sum": { "value": 0.0021615954285714276, "min": 0.0021615954285714276, "max": 0.11406218282857142, "count": 35 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008346346206963062, "min": 0.008346346206963062, "max": 0.56560879945755, "count": 35 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11684884130954742, "min": 0.11684884130954742, "max": 3.959261655807495, "count": 35 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 398.17333333333335, "min": 301.77, "max": 999.0, "count": 35 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29863.0, "min": 15984.0, "max": 32444.0, "count": 35 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3412315557269674, "min": -1.0000000521540642, "max": 1.6733934647687103, "count": 35 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 101.93359823524952, "min": -31.99760165810585, "max": 160.0169977992773, "count": 35 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3412315557269674, "min": -1.0000000521540642, "max": 1.6733934647687103, "count": 35 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 101.93359823524952, "min": -31.99760165810585, "max": 160.0169977992773, "count": 35 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03547075613773574, "min": 0.03270587023606905, "max": 12.225353107787669, "count": 35 }, "Pyramids.Policy.RndReward.sum": { "value": 2.6957774664679164, "min": 2.6957774664679164, "max": 195.6056497246027, "count": 35 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 35 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 35 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1681960905", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.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": "1681963326" }, "total": 2421.109362538, "count": 1, "self": 0.47768648400005986, "children": { "run_training.setup": { "total": 0.11630556699992667, "count": 1, "self": 0.11630556699992667 }, "TrainerController.start_learning": { "total": 2420.515370487, "count": 1, "self": 1.7958764960617373, "children": { "TrainerController._reset_env": { "total": 5.2178114090002055, "count": 1, "self": 5.2178114090002055 }, "TrainerController.advance": { "total": 2413.401094762938, "count": 67093, "self": 1.796873218903329, "children": { "env_step": { "total": 1741.875181138057, "count": 67093, "self": 1612.659379732197, "children": { "SubprocessEnvManager._take_step": { "total": 128.12361271797772, "count": 67093, "self": 5.665506123957584, "children": { "TorchPolicy.evaluate": { "total": 122.45810659402014, "count": 65702, "self": 122.45810659402014 } } }, "workers": { "total": 1.0921886878822988, "count": 67093, "self": 0.0, "children": { "worker_root": { "total": 2414.1270368039814, "count": 67093, "is_parallel": true, "self": 935.145893278981, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002786045999982889, "count": 1, "is_parallel": true, "self": 0.0007988290003595466, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019872169996233424, "count": 8, "is_parallel": true, "self": 0.0019872169996233424 } } }, "UnityEnvironment.step": { "total": 0.049496197999815195, "count": 1, "is_parallel": true, "self": 0.0006019560000822821, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048212699994110153, "count": 1, "is_parallel": true, "self": 0.00048212699994110153 }, "communicator.exchange": { "total": 0.04644811199977994, "count": 1, "is_parallel": true, "self": 0.04644811199977994 }, "steps_from_proto": { "total": 0.0019640030000118713, "count": 1, "is_parallel": true, "self": 0.0005176929994377133, "children": { "_process_rank_one_or_two_observation": { "total": 0.001446310000574158, "count": 8, "is_parallel": true, "self": 0.001446310000574158 } } } } } } }, "UnityEnvironment.step": { "total": 1478.9811435250003, "count": 67092, "is_parallel": true, "self": 36.48652579811278, "children": { "UnityEnvironment._generate_step_input": { "total": 27.319560468893087, "count": 67092, "is_parallel": true, "self": 27.319560468893087 }, "communicator.exchange": { "total": 1302.7573370269934, "count": 67092, "is_parallel": true, "self": 1302.7573370269934 }, "steps_from_proto": { "total": 112.41772023100111, "count": 67092, "is_parallel": true, "self": 25.046419755153238, "children": { "_process_rank_one_or_two_observation": { "total": 87.37130047584787, "count": 536736, "is_parallel": true, "self": 87.37130047584787 } } } } } } } } } } }, "trainer_advance": { "total": 669.7290404059777, "count": 67093, "self": 3.1523484367894525, "children": { "process_trajectory": { "total": 122.19212334917938, "count": 67093, "self": 121.98524225617984, "children": { "RLTrainer._checkpoint": { "total": 0.20688109299953794, "count": 2, "self": 0.20688109299953794 } } }, "_update_policy": { "total": 544.3845686200088, "count": 470, "self": 351.2483496599807, "children": { "TorchPPOOptimizer.update": { "total": 193.13621896002815, "count": 23916, "self": 193.13621896002815 } } } } } } }, "trainer_threads": { "total": 9.499999578110874e-07, "count": 1, "self": 9.499999578110874e-07 }, "TrainerController._save_models": { "total": 0.10058686899992608, "count": 1, "self": 0.0014441250004892936, "children": { "RLTrainer._checkpoint": { "total": 0.09914274399943679, "count": 1, "self": 0.09914274399943679 } } } } } } }