{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.8283917307853699, "min": 0.8020301461219788, "max": 1.6015796661376953, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 7554.9326171875, "min": 7554.9326171875, "max": 17268.2734375, "count": 100 }, "Pyramids.Step.mean": { "value": 999940.0, "min": 9984.0, "max": 999940.0, "count": 100 }, "Pyramids.Step.sum": { "value": 999940.0, "min": 9984.0, "max": 999940.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0447661429643631, "min": -0.1097426638007164, "max": 0.13013413548469543, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 7.207348823547363, "min": -17.88805389404297, "max": 21.211864471435547, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07456114900061021, "min": 0.06083449810588112, "max": 0.07743057642752925, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.29824459600244085, "min": 0.19074411292759968, "max": 0.38715288213764626, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.007931709443576384, "min": 1.1890522964739391e-05, "max": 0.018531277864288615, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.03172683777430554, "min": 4.7562091858957564e-05, "max": 0.08221641838948321, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4482745172750017e-06, "min": 1.4482745172750017e-06, "max": 0.0002982464005845333, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 5.793098069100007e-06, "min": 5.793098069100007e-06, "max": 0.0011814144061951999, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10048272500000001, "min": 0.10048272500000001, "max": 0.19941546666666668, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.40193090000000004, "min": 0.40193090000000004, "max": 0.8875904, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 3.408797750000003e-05, "min": 3.408797750000003e-05, "max": 0.004970831786666667, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.00013635191000000013, "min": 0.00013635191000000013, "max": 0.01969085952, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 841.7, "min": 591.6666666666666, "max": 999.0, "count": 92 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 8417.0, "min": 999.0, "max": 15984.0, "count": 92 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.20163337824245295, "min": -1.0000000447034836, "max": 0.7658666368159983, "count": 94 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -2.4196005389094353, "min": -16.000000715255737, "max": 6.892799731343985, "count": 94 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.20163337824245295, "min": -1.0000000447034836, "max": 0.7658666368159983, "count": 94 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -2.4196005389094353, "min": -16.000000715255737, "max": 6.892799731343985, "count": 94 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1717087125", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/ml-agents/SnowballTarget.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training4 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1717088955" }, "total": 1829.5406555079999, "count": 1, "self": 0.4752990020001562, "children": { "run_training.setup": { "total": 0.05074972899996055, "count": 1, "self": 0.05074972899996055 }, "TrainerController.start_learning": { "total": 1829.0146067769997, "count": 1, "self": 1.9408965900395287, "children": { "TrainerController._reset_env": { "total": 2.7365440579999927, "count": 1, "self": 2.7365440579999927 }, "TrainerController.advance": { "total": 1824.28012635896, "count": 63005, "self": 1.0176860509614016, "children": { "env_step": { "total": 1823.2624403079985, "count": 63005, "self": 1402.854430154005, "children": { "SubprocessEnvManager._take_step": { "total": 419.37490910801216, "count": 63005, "self": 6.01051848801302, "children": { "TorchPolicy.evaluate": { "total": 413.36439061999914, "count": 62536, "self": 413.36439061999914 } } }, "workers": { "total": 1.0331010459813115, "count": 63005, "self": 0.0, "children": { "worker_root": { "total": 1824.4762694240076, "count": 63005, "is_parallel": true, "self": 645.64677495098, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001895098999966649, "count": 1, "is_parallel": true, "self": 0.0005678829998601032, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013272160001065458, "count": 8, "is_parallel": true, "self": 0.0013272160001065458 } } }, "UnityEnvironment.step": { "total": 0.05189594500001249, "count": 1, "is_parallel": true, "self": 0.0006624570000326457, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004858439999679831, "count": 1, "is_parallel": true, "self": 0.0004858439999679831 }, "communicator.exchange": { "total": 0.04889690499999233, "count": 1, "is_parallel": true, "self": 0.04889690499999233 }, "steps_from_proto": { "total": 0.00185073900001953, "count": 1, "is_parallel": true, "self": 0.0004283409999743526, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014223980000451775, "count": 8, "is_parallel": true, "self": 0.0014223980000451775 } } } } } } }, "UnityEnvironment.step": { "total": 1178.8294944730276, "count": 63004, "is_parallel": true, "self": 33.7593119580099, "children": { "UnityEnvironment._generate_step_input": { "total": 22.888582343980886, "count": 63004, "is_parallel": true, "self": 22.888582343980886 }, "communicator.exchange": { "total": 1020.0726152700129, "count": 63004, "is_parallel": true, "self": 1020.0726152700129 }, "steps_from_proto": { "total": 102.10898490102386, "count": 63004, "is_parallel": true, "self": 21.46584603908218, "children": { "_process_rank_one_or_two_observation": { "total": 80.64313886194168, "count": 504032, "is_parallel": true, "self": 80.64313886194168 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00010620000011840602, "count": 1, "self": 0.00010620000011840602, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1813.5115776959706, "count": 1460613, "is_parallel": true, "self": 28.9126332509868, "children": { "process_trajectory": { "total": 754.1166744189823, "count": 1460613, "is_parallel": true, "self": 751.327448781982, "children": { "RLTrainer._checkpoint": { "total": 2.7892256370002997, "count": 20, "is_parallel": true, "self": 2.7892256370002997 } } }, "_update_policy": { "total": 1030.4822700260015, "count": 441, "is_parallel": true, "self": 319.33288989800064, "children": { "TorchPPOOptimizer.update": { "total": 711.1493801280009, "count": 22998, "is_parallel": true, "self": 711.1493801280009 } } } } } } } } }, "TrainerController._save_models": { "total": 0.056933570000182954, "count": 1, "self": 0.0008461390002594271, "children": { "RLTrainer._checkpoint": { "total": 0.05608743099992353, "count": 1, "self": 0.05608743099992353 } } } } } } }