{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4799007475376129, "min": 0.4799007475376129, "max": 1.4425519704818726, "count": 34 }, "Pyramids.Policy.Entropy.sum": { "value": 14481.4853515625, "min": 14481.4853515625, "max": 43761.2578125, "count": 34 }, "Pyramids.Step.mean": { "value": 1019998.0, "min": 29925.0, "max": 1019998.0, "count": 34 }, "Pyramids.Step.sum": { "value": 1019998.0, "min": 29925.0, "max": 1019998.0, "count": 34 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.630422830581665, "min": -0.10637927800416946, "max": 0.6738637089729309, "count": 34 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 178.40966796875, "min": -25.637405395507812, "max": 192.7250213623047, "count": 34 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.011764978058636189, "min": -0.03138011693954468, "max": 0.39795830845832825, "count": 34 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.329488754272461, "min": -8.190210342407227, "max": 94.31611633300781, "count": 34 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06433102600799849, "min": 0.06433102600799849, "max": 0.07317338876670136, "count": 34 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.900634364111979, "min": 0.49127410598826493, "max": 1.0436711947065, "count": 34 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015107533874078063, "min": 0.0003881496569336964, "max": 0.016250818733358104, "count": 34 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21150547423709287, "min": 0.00426964622627066, "max": 0.22804282070622622, "count": 34 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00019946601208276903, "min": 0.00019946601208276903, "max": 0.00029841135767240477, "count": 34 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0027925241691587666, "min": 0.0020888795037068333, "max": 0.003927576290807934, "count": 34 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.16648865952380956, "min": 0.16648865952380956, "max": 0.19947045238095237, "count": 34 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.330841233333334, "min": 1.3962931666666667, "max": 2.7674513333333333, "count": 34 }, "Pyramids.Policy.Beta.mean": { "value": 0.00665221708642857, "min": 0.00665221708642857, "max": 0.009947098192857143, "count": 34 }, "Pyramids.Policy.Beta.sum": { "value": 0.09313103920999999, "min": 0.06962968735, "max": 0.13092828746, "count": 34 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009384281001985073, "min": 0.008668171241879463, "max": 0.47065672278404236, "count": 34 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13137993216514587, "min": 0.12135440111160278, "max": 3.2945971488952637, "count": 34 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 301.0, "min": 299.9306930693069, "max": 999.0, "count": 34 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30100.0, "min": 16724.0, "max": 33286.0, "count": 34 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5989699848741292, "min": -0.9999290844125133, "max": 1.661799988193998, "count": 34 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 159.89699848741293, "min": -30.99780161678791, "max": 171.1653987839818, "count": 34 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5989699848741292, "min": -0.9999290844125133, "max": 1.661799988193998, "count": 34 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 159.89699848741293, "min": -30.99780161678791, "max": 171.1653987839818, "count": 34 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0293618603797222, "min": 0.02897740167234199, "max": 9.478499167105731, "count": 34 }, "Pyramids.Policy.RndReward.sum": { "value": 2.93618603797222, "min": 2.6064819101520698, "max": 161.13448584079742, "count": 34 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 34 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 34 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1739028454", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739032089" }, "total": 3635.248275418, "count": 1, "self": 0.7074317260003227, "children": { "run_training.setup": { "total": 0.03042054399998051, "count": 1, "self": 0.03042054399998051 }, "TrainerController.start_learning": { "total": 3634.510423148, "count": 1, "self": 2.515407049029818, "children": { "TrainerController._reset_env": { "total": 3.651253501000042, "count": 1, "self": 3.651253501000042 }, "TrainerController.advance": { "total": 3628.342446476971, "count": 66853, "self": 2.6803199989240056, "children": { "env_step": { "total": 2408.1284270030164, "count": 66853, "self": 2222.893290893089, "children": { "SubprocessEnvManager._take_step": { "total": 183.73253783290988, "count": 66853, "self": 8.062434674910037, "children": { "TorchPolicy.evaluate": { "total": 175.67010315799985, "count": 65400, "self": 175.67010315799985 } } }, "workers": { "total": 1.502598277017114, "count": 66852, "self": 0.0, "children": { "worker_root": { "total": 3626.1912841720696, "count": 66852, "is_parallel": true, "self": 1599.2283714050293, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007412913000052868, "count": 1, "is_parallel": true, "self": 0.0044866390003335255, "children": { "_process_rank_one_or_two_observation": { "total": 0.002926273999719342, "count": 8, "is_parallel": true, "self": 0.002926273999719342 } } }, "UnityEnvironment.step": { "total": 0.06473732100005236, "count": 1, "is_parallel": true, "self": 0.0006852220000155285, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005385140000271349, "count": 1, "is_parallel": true, "self": 0.0005385140000271349 }, "communicator.exchange": { "total": 0.06142405699995379, "count": 1, "is_parallel": true, "self": 0.06142405699995379 }, "steps_from_proto": { "total": 0.002089528000055907, "count": 1, "is_parallel": true, "self": 0.0005739370001265343, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015155909999293726, "count": 8, "is_parallel": true, "self": 0.0015155909999293726 } } } } } } }, "UnityEnvironment.step": { "total": 2026.9629127670403, "count": 66851, "is_parallel": true, "self": 51.4139171500417, "children": { "UnityEnvironment._generate_step_input": { "total": 32.99150247503178, "count": 66851, "is_parallel": true, "self": 32.99150247503178 }, "communicator.exchange": { "total": 1805.3835107259538, "count": 66851, "is_parallel": true, "self": 1805.3835107259538 }, "steps_from_proto": { "total": 137.17398241601313, "count": 66851, "is_parallel": true, "self": 29.841580390224976, "children": { "_process_rank_one_or_two_observation": { "total": 107.33240202578816, "count": 534808, "is_parallel": true, "self": 107.33240202578816 } } } } } } } } } } }, "trainer_advance": { "total": 1217.5336994750305, "count": 66852, "self": 4.9865148619760475, "children": { "process_trajectory": { "total": 182.5841518020561, "count": 66852, "self": 182.16526377105583, "children": { "RLTrainer._checkpoint": { "total": 0.4188880310002787, "count": 2, "self": 0.4188880310002787 } } }, "_update_policy": { "total": 1029.9630328109984, "count": 474, "self": 401.5927613909324, "children": { "TorchPPOOptimizer.update": { "total": 628.3702714200659, "count": 23829, "self": 628.3702714200659 } } } } } } }, "trainer_threads": { "total": 1.6069998309831135e-06, "count": 1, "self": 1.6069998309831135e-06 }, "TrainerController._save_models": { "total": 0.0013145139992047916, "count": 1, "self": 3.671999911603052e-05, "children": { "RLTrainer._checkpoint": { "total": 0.001277794000088761, "count": 1, "self": 0.001277794000088761 } } } } } } }