{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3324196934700012, "min": 0.30338501930236816, "max": 1.6091679334640503, "count": 935 }, "Pyramids.Policy.Entropy.sum": { "value": 436.1346435546875, "min": 143.02752685546875, "max": 3295.575927734375, "count": 935 }, "Pyramids.Step.mean": { "value": 999950.0, "min": 896.0, "max": 999950.0, "count": 1000 }, "Pyramids.Step.sum": { "value": 999950.0, "min": 896.0, "max": 999950.0, "count": 1000 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7542731761932373, "min": -0.14840197563171387, "max": 0.9465013146400452, "count": 1000 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 9.051278114318848, "min": -1.187215805053711, "max": 11.358016014099121, "count": 1000 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0011145133757963777, "min": -0.06977647542953491, "max": 0.5489682555198669, "count": 1000 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.01337416097521782, "min": -0.6279882788658142, "max": 4.3917460441589355, "count": 1000 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06121266016270965, "min": 0.048903413116931915, "max": 0.09571001154836267, "count": 450 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.06121266016270965, "min": 0.048903413116931915, "max": 0.09571001154836267, "count": 450 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01624758077862983, "min": 8.447625926540543e-05, "max": 0.02875153426430188, "count": 450 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.01624758077862983, "min": 8.447625926540543e-05, "max": 0.02875153426430188, "count": 450 }, "Pyramids.Policy.LearningRate.mean": { "value": 3.573998809000159e-07, "min": 3.573998809000159e-07, "max": 0.0002987712004096, "count": 450 }, "Pyramids.Policy.LearningRate.sum": { "value": 3.573998809000159e-07, "min": 3.573998809000159e-07, "max": 0.0002987712004096, "count": 450 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10011910000000002, "min": 0.10011910000000002, "max": 0.19959039999999997, "count": 450 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.10011910000000002, "min": 0.10011910000000002, "max": 0.19959039999999997, "count": 450 }, "Pyramids.Policy.Beta.mean": { "value": 2.1898090000000534e-05, "min": 2.1898090000000534e-05, "max": 0.009959080960000002, "count": 450 }, "Pyramids.Policy.Beta.sum": { "value": 2.1898090000000534e-05, "min": 2.1898090000000534e-05, "max": 0.009959080960000002, "count": 450 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00959926936775446, "min": 0.009250455535948277, "max": 1.0069694519042969, "count": 450 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.00959926936775446, "min": 0.009250455535948277, "max": 1.0069694519042969, "count": 450 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 220.66666666666666, "min": 29.0, "max": 999.0, "count": 705 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 1324.0, "min": 29.0, "max": 15984.0, "count": 705 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7100000147308623, "min": -1.0000000521540642, "max": 1.9709999561309814, "count": 726 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 11.970000103116035, "min": -9.000000469386578, "max": 13.569999918341637, "count": 726 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7100000147308623, "min": -1.0000000521540642, "max": 1.9709999561309814, "count": 726 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 11.970000103116035, "min": -9.000000469386578, "max": 13.569999918341637, "count": 726 }, "Pyramids.Policy.RndReward.mean": { "value": 0.028489987748408958, "min": 0.008192313835024834, "max": 10.31822442677286, "count": 726 }, "Pyramids.Policy.RndReward.sum": { "value": 0.1994299142388627, "min": 0.008192313835024834, "max": 92.86401984095573, "count": 726 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1736832738", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1736835040" }, "total": 2301.5398536719995, "count": 1, "self": 0.47922753199964063, "children": { "run_training.setup": { "total": 0.054998270999931265, "count": 1, "self": 0.054998270999931265 }, "TrainerController.start_learning": { "total": 2301.005627869, "count": 1, "self": 1.3715098499815213, "children": { "TrainerController._reset_env": { "total": 2.202947640000275, "count": 1, "self": 2.202947640000275 }, "TrainerController.advance": { "total": 2297.3176517520187, "count": 63922, "self": 1.495954733924009, "children": { "env_step": { "total": 1605.1533933310784, "count": 63922, "self": 1452.564561545947, "children": { "SubprocessEnvManager._take_step": { "total": 151.77136065200557, "count": 63922, "self": 4.65436657400187, "children": { "TorchPolicy.evaluate": { "total": 147.1169940780037, "count": 62567, "self": 147.1169940780037 } } }, "workers": { "total": 0.817471133125764, "count": 63922, "self": 0.0, "children": { "worker_root": { "total": 2295.4157969049475, "count": 63922, "is_parallel": true, "self": 961.6718560099971, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002035882999734895, "count": 1, "is_parallel": true, "self": 0.0006584000011571334, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013774829985777615, "count": 8, "is_parallel": true, "self": 0.0013774829985777615 } } }, "UnityEnvironment.step": { "total": 0.053072605000124895, "count": 1, "is_parallel": true, "self": 0.0006144000008134753, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004944269994666683, "count": 1, "is_parallel": true, "self": 0.0004944269994666683 }, "communicator.exchange": { "total": 0.0502241590002086, "count": 1, "is_parallel": true, "self": 0.0502241590002086 }, "steps_from_proto": { "total": 0.00173961899963615, "count": 1, "is_parallel": true, "self": 0.0003545740000845399, "children": { "_process_rank_one_or_two_observation": { "total": 0.00138504499955161, "count": 8, "is_parallel": true, "self": 0.00138504499955161 } } } } } } }, "UnityEnvironment.step": { "total": 1333.7439408949504, "count": 63921, "is_parallel": true, "self": 33.012319721001404, "children": { "UnityEnvironment._generate_step_input": { "total": 22.66215186291265, "count": 63921, "is_parallel": true, "self": 22.66215186291265 }, "communicator.exchange": { "total": 1180.3075301681174, "count": 63921, "is_parallel": true, "self": 1180.3075301681174 }, "steps_from_proto": { "total": 97.76193914291889, "count": 63921, "is_parallel": true, "self": 20.154615688991726, "children": { "_process_rank_one_or_two_observation": { "total": 77.60732345392717, "count": 511368, "is_parallel": true, "self": 77.60732345392717 } } } } } } } } } } }, "trainer_advance": { "total": 690.6683036870163, "count": 63922, "self": 2.7086135477293283, "children": { "process_trajectory": { "total": 138.23289422428115, "count": 63922, "self": 137.99748983228073, "children": { "RLTrainer._checkpoint": { "total": 0.23540439200041874, "count": 2, "self": 0.23540439200041874 } } }, "_update_policy": { "total": 549.7267959150058, "count": 450, "self": 306.7815066370531, "children": { "TorchPPOOptimizer.update": { "total": 242.94528927795272, "count": 22803, "self": 242.94528927795272 } } } } } } }, "trainer_threads": { "total": 1.318999238719698e-06, "count": 1, "self": 1.318999238719698e-06 }, "TrainerController._save_models": { "total": 0.11351730800015503, "count": 1, "self": 0.0015188730003501405, "children": { "RLTrainer._checkpoint": { "total": 0.11199843499980489, "count": 1, "self": 0.11199843499980489 } } } } } } }