{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.15111464262008667, "min": 0.15111464262008667, "max": 1.4325040578842163, "count": 89 }, "Pyramids.Policy.Entropy.sum": { "value": 4531.021484375, "min": 4531.021484375, "max": 43456.44140625, "count": 89 }, "Pyramids.Step.mean": { "value": 2669982.0, "min": 29952.0, "max": 2669982.0, "count": 89 }, "Pyramids.Step.sum": { "value": 2669982.0, "min": 29952.0, "max": 2669982.0, "count": 89 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5815648436546326, "min": -0.11563204973936081, "max": 0.6978034377098083, "count": 89 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 162.83815002441406, "min": -28.098588943481445, "max": 201.66519165039062, "count": 89 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0048854779452085495, "min": -0.0012113683624193072, "max": 0.44748809933662415, "count": 89 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.3679338693618774, "min": -0.3428172469139099, "max": 106.05467987060547, "count": 89 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07091879857485071, "min": 0.06389800343685709, "max": 0.07378497364204761, "count": 89 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9928631800479101, "min": 0.481007311906968, "max": 1.0586867328092922, "count": 89 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015049542405731265, "min": 8.12995156895757e-05, "max": 0.01578679219618243, "count": 89 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2106935936802377, "min": 0.0011381932196540597, "max": 0.22101509074655398, "count": 89 }, "Pyramids.Policy.LearningRate.mean": { "value": 3.446695279675953e-05, "min": 3.446695279675953e-05, "max": 0.00029838354339596195, "count": 89 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0004825373391546334, "min": 0.0004825373391546334, "max": 0.003969224076925333, "count": 89 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.11148895476190476, "min": 0.11148895476190476, "max": 0.19946118095238097, "count": 89 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5608453666666666, "min": 1.3897045333333333, "max": 2.7524597333333336, "count": 89 }, "Pyramids.Policy.Beta.mean": { "value": 0.0011577465807142858, "min": 0.0011577465807142858, "max": 0.009946171977142856, "count": 89 }, "Pyramids.Policy.Beta.sum": { "value": 0.016208452130000002, "min": 0.016208452130000002, "max": 0.13231515919999998, "count": 89 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005369116552174091, "min": 0.005265297833830118, "max": 0.39209750294685364, "count": 89 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07516763359308243, "min": 0.074711874127388, "max": 2.744682550430298, "count": 89 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 333.5833333333333, "min": 271.08, "max": 999.0, "count": 89 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32024.0, "min": 15984.0, "max": 32792.0, "count": 89 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5795494530546037, "min": -1.0000000521540642, "max": 1.702336621830369, "count": 89 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 150.05719804018736, "min": -32.000001668930054, "max": 179.65639878809452, "count": 89 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5795494530546037, "min": -1.0000000521540642, "max": 1.702336621830369, "count": 89 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 150.05719804018736, "min": -32.000001668930054, "max": 179.65639878809452, "count": 89 }, "Pyramids.Policy.RndReward.mean": { "value": 0.018861757409084884, "min": 0.015193429891078268, "max": 7.542981471866369, "count": 89 }, "Pyramids.Policy.RndReward.sum": { "value": 1.7918669538630638, "min": 1.5193429891078267, "max": 120.68770354986191, "count": 89 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 89 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 89 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1700686906", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700692804" }, "total": 5898.031150867, "count": 1, "self": 0.4112637910002377, "children": { "run_training.setup": { "total": 0.04540667800029041, "count": 1, "self": 0.04540667800029041 }, "TrainerController.start_learning": { "total": 5897.574480398, "count": 1, "self": 3.310677008887069, "children": { "TrainerController._reset_env": { "total": 5.24040349400002, "count": 1, "self": 5.24040349400002 }, "TrainerController.advance": { "total": 5888.908088859113, "count": 172951, "self": 3.547196481023093, "children": { "env_step": { "total": 4194.582715425147, "count": 172951, "self": 3861.8882753959015, "children": { "SubprocessEnvManager._take_step": { "total": 330.63175566214886, "count": 172951, "self": 12.244220178207797, "children": { "TorchPolicy.evaluate": { "total": 318.38753548394106, "count": 168492, "self": 318.38753548394106 } } }, "workers": { "total": 2.062684367097063, "count": 172950, "self": 0.0, "children": { "worker_root": { "total": 5886.108775543811, "count": 172950, "is_parallel": true, "self": 2326.244992923934, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001818195000396372, "count": 1, "is_parallel": true, "self": 0.0006236760009414866, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011945189994548855, "count": 8, "is_parallel": true, "self": 0.0011945189994548855 } } }, "UnityEnvironment.step": { "total": 0.0979518420003842, "count": 1, "is_parallel": true, "self": 0.000555074000658351, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004650779997064092, "count": 1, "is_parallel": true, "self": 0.0004650779997064092 }, "communicator.exchange": { "total": 0.09525192199998855, "count": 1, "is_parallel": true, "self": 0.09525192199998855 }, "steps_from_proto": { "total": 0.00167976800003089, "count": 1, "is_parallel": true, "self": 0.0003795869988607592, "children": { "_process_rank_one_or_two_observation": { "total": 0.001300181001170131, "count": 8, "is_parallel": true, "self": 0.001300181001170131 } } } } } } }, "UnityEnvironment.step": { "total": 3559.863782619877, "count": 172949, "is_parallel": true, "self": 89.39608420480681, "children": { "UnityEnvironment._generate_step_input": { "total": 61.501272881152545, "count": 172949, "is_parallel": true, "self": 61.501272881152545 }, "communicator.exchange": { "total": 3157.480528350006, "count": 172949, "is_parallel": true, "self": 3157.480528350006 }, "steps_from_proto": { "total": 251.48589718391167, "count": 172949, "is_parallel": true, "self": 49.3037058051832, "children": { "_process_rank_one_or_two_observation": { "total": 202.18219137872848, "count": 1383592, "is_parallel": true, "self": 202.18219137872848 } } } } } } } } } } }, "trainer_advance": { "total": 1690.7781769529433, "count": 172950, "self": 6.797328798783383, "children": { "process_trajectory": { "total": 336.11463547313997, "count": 172950, "self": 335.70519010713997, "children": { "RLTrainer._checkpoint": { "total": 0.4094453659999999, "count": 5, "self": 0.4094453659999999 } } }, "_update_policy": { "total": 1347.86621268102, "count": 1246, "self": 806.8264153978644, "children": { "TorchPPOOptimizer.update": { "total": 541.0397972831556, "count": 61500, "self": 541.0397972831556 } } } } } } }, "trainer_threads": { "total": 1.2790005712304264e-06, "count": 1, "self": 1.2790005712304264e-06 }, "TrainerController._save_models": { "total": 0.11530975699861301, "count": 1, "self": 0.001877035998404608, "children": { "RLTrainer._checkpoint": { "total": 0.1134327210002084, "count": 1, "self": 0.1134327210002084 } } } } } } }