{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.43163731694221497, "min": 0.4153560400009155, "max": 1.4269607067108154, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12942.212890625, "min": 12440.744140625, "max": 43288.28125, "count": 33 }, "Pyramids.Step.mean": { "value": 989956.0, "min": 29952.0, "max": 989956.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989956.0, "min": 29952.0, "max": 989956.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4822089374065399, "min": -0.10434004664421082, "max": 0.5244603157043457, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 129.71420288085938, "min": -25.354631423950195, "max": 142.65321350097656, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.055451054126024246, "min": -0.013870149850845337, "max": 0.2779541611671448, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 14.916333198547363, "min": -3.7726807594299316, "max": 67.26490783691406, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06502017837354085, "min": 0.06478529941458772, "max": 0.07438894039519248, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9753026756031128, "min": 0.5207225827663473, "max": 1.0372913038202873, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01691120349892622, "min": 0.000710129963435088, "max": 0.01691120349892622, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2536680524838933, "min": 0.007811429597785968, "max": 0.2536680524838933, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.560517479859996e-06, "min": 7.560517479859996e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011340776219789995, "min": 0.00011340776219789995, "max": 0.0036333373888875996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252014, "min": 0.10252014, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5378021, "min": 1.3886848, "max": 2.6111124000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002617619859999999, "min": 0.0002617619859999999, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003926429789999999, "min": 0.003926429789999999, "max": 0.12113012876000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007886173203587532, "min": 0.007886173203587532, "max": 0.4306356906890869, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11829259991645813, "min": 0.11122598499059677, "max": 3.0144498348236084, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 375.4625, "min": 341.685393258427, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30037.0, "min": 15984.0, "max": 33700.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4244774755090475, "min": -1.0000000521540642, "max": 1.568388743012139, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 113.9581980407238, "min": -29.70800169557333, "max": 139.58659812808037, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4244774755090475, "min": -1.0000000521540642, "max": 1.568388743012139, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 113.9581980407238, "min": -29.70800169557333, "max": 139.58659812808037, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.030213625391115783, "min": 0.030213625391115783, "max": 9.195544684305787, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.4170900312892627, "min": 2.3112042422872037, "max": 147.1287149488926, "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": "1722576107", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1722578308" }, "total": 2200.491875445, "count": 1, "self": 1.0929356330007067, "children": { "run_training.setup": { "total": 0.051451882000037585, "count": 1, "self": 0.051451882000037585 }, "TrainerController.start_learning": { "total": 2199.3474879299993, "count": 1, "self": 1.5632833710096747, "children": { "TrainerController._reset_env": { "total": 1.8111348999998427, "count": 1, "self": 1.8111348999998427 }, "TrainerController.advance": { "total": 2195.84831694499, "count": 63811, "self": 1.3546107928441415, "children": { "env_step": { "total": 1569.1203841080549, "count": 63811, "self": 1439.6724325361063, "children": { "SubprocessEnvManager._take_step": { "total": 128.6550199599501, "count": 63811, "self": 4.655809844893611, "children": { "TorchPolicy.evaluate": { "total": 123.99921011505648, "count": 62564, "self": 123.99921011505648 } } }, "workers": { "total": 0.7929316119984833, "count": 63811, "self": 0.0, "children": { "worker_root": { "total": 2194.162218524977, "count": 63811, "is_parallel": true, "self": 873.4329671159853, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020412250000845233, "count": 1, "is_parallel": true, "self": 0.0006687819995931932, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013724430004913302, "count": 8, "is_parallel": true, "self": 0.0013724430004913302 } } }, "UnityEnvironment.step": { "total": 0.048146164000172575, "count": 1, "is_parallel": true, "self": 0.0006165910001527664, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044886499995300255, "count": 1, "is_parallel": true, "self": 0.00044886499995300255 }, "communicator.exchange": { "total": 0.04546441799993772, "count": 1, "is_parallel": true, "self": 0.04546441799993772 }, "steps_from_proto": { "total": 0.0016162900001290836, "count": 1, "is_parallel": true, "self": 0.0003537170002800849, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012625729998489987, "count": 8, "is_parallel": true, "self": 0.0012625729998489987 } } } } } } }, "UnityEnvironment.step": { "total": 1320.7292514089918, "count": 63810, "is_parallel": true, "self": 33.13686204685723, "children": { "UnityEnvironment._generate_step_input": { "total": 23.47245547602256, "count": 63810, "is_parallel": true, "self": 23.47245547602256 }, "communicator.exchange": { "total": 1165.7749696280557, "count": 63810, "is_parallel": true, "self": 1165.7749696280557 }, "steps_from_proto": { "total": 98.34496425805628, "count": 63810, "is_parallel": true, "self": 20.01244563117075, "children": { "_process_rank_one_or_two_observation": { "total": 78.33251862688553, "count": 510480, "is_parallel": true, "self": 78.33251862688553 } } } } } } } } } } }, "trainer_advance": { "total": 625.3733220440911, "count": 63811, "self": 2.494954543097265, "children": { "process_trajectory": { "total": 128.83818862299495, "count": 63811, "self": 128.59726045299476, "children": { "RLTrainer._checkpoint": { "total": 0.2409281700001884, "count": 2, "self": 0.2409281700001884 } } }, "_update_policy": { "total": 494.04017887799887, "count": 451, "self": 292.51333045900583, "children": { "TorchPPOOptimizer.update": { "total": 201.52684841899304, "count": 22782, "self": 201.52684841899304 } } } } } } }, "trainer_threads": { "total": 1.491000148234889e-06, "count": 1, "self": 1.491000148234889e-06 }, "TrainerController._save_models": { "total": 0.12475122299929353, "count": 1, "self": 0.0019286069991721888, "children": { "RLTrainer._checkpoint": { "total": 0.12282261600012134, "count": 1, "self": 0.12282261600012134 } } } } } } }