{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5893661975860596, "min": 0.568692147731781, "max": 1.4758681058883667, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17784.71484375, "min": 16900.833984375, "max": 44771.93359375, "count": 33 }, "Pyramids.Step.mean": { "value": 989898.0, "min": 29952.0, "max": 989898.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989898.0, "min": 29952.0, "max": 989898.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2101958990097046, "min": -0.1027693897485733, "max": 0.2590601146221161, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 53.599952697753906, "min": -24.664653778076172, "max": 66.0603256225586, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.03355784714221954, "min": -0.03355784714221954, "max": 0.21750079095363617, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -8.5572509765625, "min": -8.5572509765625, "max": 52.200191497802734, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07104361438125904, "min": 0.06510643669007397, "max": 0.07418223902032015, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9946106013376266, "min": 0.519275673142241, "max": 1.008624666327081, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01049372204743988, "min": 0.0002906726545064113, "max": 0.01233073811211701, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.14691210866415833, "min": 0.004069417163089758, "max": 0.17263033356963814, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.538883201357144e-06, "min": 7.538883201357144e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010554436481900002, "min": 0.00010554436481900002, "max": 0.0031388078537308, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251292857142857, "min": 0.10251292857142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.435181, "min": 1.3886848, "max": 2.3587890000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002610415642857144, "min": 0.0002610415642857144, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036545819000000012, "min": 0.0036545819000000012, "max": 0.10465229308, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010782822966575623, "min": 0.010527980513870716, "max": 0.34698358178138733, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15095952153205872, "min": 0.14739172160625458, "max": 2.428884983062744, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 574.14, "min": 542.9433962264151, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28707.0, "min": 15984.0, "max": 32475.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.9457479740679264, "min": -1.0000000521540642, "max": 1.1928377046056513, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 47.28739870339632, "min": -31.99920167028904, "max": 63.22039834409952, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.9457479740679264, "min": -1.0000000521540642, "max": 1.1928377046056513, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 47.28739870339632, "min": -31.99920167028904, "max": 63.22039834409952, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06451316221151501, "min": 0.06033620439614784, "max": 6.906614917330444, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2256581105757505, "min": 3.1978188329958357, "max": 110.5058386772871, "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": "1679316152", "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": "1679318204" }, "total": 2052.286290494, "count": 1, "self": 0.424629611999535, "children": { "run_training.setup": { "total": 0.12311337300002378, "count": 1, "self": 0.12311337300002378 }, "TrainerController.start_learning": { "total": 2051.738547509, "count": 1, "self": 1.313889352023125, "children": { "TrainerController._reset_env": { "total": 7.3238711510000485, "count": 1, "self": 7.3238711510000485 }, "TrainerController.advance": { "total": 2043.0090209279774, "count": 63266, "self": 1.3400074288706492, "children": { "env_step": { "total": 1431.1082236640802, "count": 63266, "self": 1326.6766883310645, "children": { "SubprocessEnvManager._take_step": { "total": 103.66538029603998, "count": 63266, "self": 4.591618385969923, "children": { "TorchPolicy.evaluate": { "total": 99.07376191007006, "count": 62557, "self": 99.07376191007006 } } }, "workers": { "total": 0.7661550369757606, "count": 63266, "self": 0.0, "children": { "worker_root": { "total": 2047.5656384768954, "count": 63266, "is_parallel": true, "self": 830.9217218268793, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002646167999955651, "count": 1, "is_parallel": true, "self": 0.0008792199998879369, "children": { "_process_rank_one_or_two_observation": { "total": 0.001766948000067714, "count": 8, "is_parallel": true, "self": 0.001766948000067714 } } }, "UnityEnvironment.step": { "total": 0.04286649799996667, "count": 1, "is_parallel": true, "self": 0.0005059499999333639, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045700200007559033, "count": 1, "is_parallel": true, "self": 0.00045700200007559033 }, "communicator.exchange": { "total": 0.039992156999915096, "count": 1, "is_parallel": true, "self": 0.039992156999915096 }, "steps_from_proto": { "total": 0.0019113890000426181, "count": 1, "is_parallel": true, "self": 0.000656427000194526, "children": { "_process_rank_one_or_two_observation": { "total": 0.001254961999848092, "count": 8, "is_parallel": true, "self": 0.001254961999848092 } } } } } } }, "UnityEnvironment.step": { "total": 1216.643916650016, "count": 63265, "is_parallel": true, "self": 30.349315270889292, "children": { "UnityEnvironment._generate_step_input": { "total": 22.11040057405671, "count": 63265, "is_parallel": true, "self": 22.11040057405671 }, "communicator.exchange": { "total": 1074.713577264007, "count": 63265, "is_parallel": true, "self": 1074.713577264007 }, "steps_from_proto": { "total": 89.4706235410631, "count": 63265, "is_parallel": true, "self": 18.9752240493126, "children": { "_process_rank_one_or_two_observation": { "total": 70.4953994917505, "count": 506120, "is_parallel": true, "self": 70.4953994917505 } } } } } } } } } } }, "trainer_advance": { "total": 610.5607898350265, "count": 63266, "self": 2.443337729064069, "children": { "process_trajectory": { "total": 113.6138300089583, "count": 63266, "self": 113.41667365895864, "children": { "RLTrainer._checkpoint": { "total": 0.19715634999965914, "count": 2, "self": 0.19715634999965914 } } }, "_update_policy": { "total": 494.50362209700415, "count": 439, "self": 314.2641772699617, "children": { "TorchPPOOptimizer.update": { "total": 180.23944482704246, "count": 22836, "self": 180.23944482704246 } } } } } } }, "trainer_threads": { "total": 8.439997145615052e-07, "count": 1, "self": 8.439997145615052e-07 }, "TrainerController._save_models": { "total": 0.0917652339999222, "count": 1, "self": 0.0015074990001266997, "children": { "RLTrainer._checkpoint": { "total": 0.0902577349997955, "count": 1, "self": 0.0902577349997955 } } } } } } }