{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6858731508255005, "min": 0.6802798509597778, "max": 1.3942458629608154, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 20674.9609375, "min": 20546.462890625, "max": 42295.84375, "count": 33 }, "Pyramids.Step.mean": { "value": 989941.0, "min": 29952.0, "max": 989941.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989941.0, "min": 29952.0, "max": 989941.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.024597879499197006, "min": -0.13248559832572937, "max": 0.024597879499197006, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 6.001882553100586, "min": -31.39908790588379, "max": 6.001882553100586, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.022965509444475174, "min": 0.015016665682196617, "max": 0.30718544125556946, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.603584289550781, "min": 3.619016408920288, "max": 74.03169250488281, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06884264806746107, "min": 0.06543262210868282, "max": 0.07405936573156563, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.963797072944455, "min": 0.48560728723331803, "max": 1.046625895714433, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.004749224507946711, "min": 6.643410630810209e-05, "max": 0.009164674884044056, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.06648914311125396, "min": 0.0009300774883134293, "max": 0.10142323369200312, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.344354694771429e-06, "min": 7.344354694771429e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010282096572680001, "min": 0.00010282096572680001, "max": 0.003140721553092899, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244808571428572, "min": 0.10244808571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342732, "min": 1.3265935999999998, "max": 2.3469071, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025456376285714293, "min": 0.00025456376285714293, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035638926800000007, "min": 0.0035638926800000007, "max": 0.10471601928999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01644657738506794, "min": 0.01644657738506794, "max": 0.4698963463306427, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.23025208711624146, "min": 0.18557105958461761, "max": 3.2892744541168213, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 877.2424242424242, "min": 807.578947368421, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28949.0, "min": 15984.0, "max": 33067.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.27149700689496414, "min": -1.2281125732697546, "max": 0.13946838108332535, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -8.959401227533817, "min": -39.29960234463215, "max": 5.299798481166363, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.27149700689496414, "min": -1.2281125732697546, "max": 0.13946838108332535, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -8.959401227533817, "min": -39.29960234463215, "max": 5.299798481166363, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.14775762952525506, "min": 0.14236713737390297, "max": 9.939638264477253, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.876001774333417, "min": 3.6765784872695804, "max": 159.03421223163605, "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": "1658945802", "python_version": "3.8.13 (default, Mar 28 2022, 06:59:08) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\sgstq\\miniconda3\\envs\\hugfrl\\Scripts\\mlagents-learn config/ppo/PyramidsRND.yaml --env=.\\trained-envs-executables\\windows\\Pyramids.exe --run-id=First Training --force", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.7.1+cu110", "numpy_version": "1.23.1", "end_time_seconds": "1658949175" }, "total": 3372.5849983, "count": 1, "self": 0.5663061999998718, "children": { "run_training.setup": { "total": 0.2578105000000006, "count": 1, "self": 0.2578105000000006 }, "TrainerController.start_learning": { "total": 3371.7608816, "count": 1, "self": 2.47262139997747, "children": { "TrainerController._reset_env": { "total": 13.3283053, "count": 1, "self": 13.3283053 }, "TrainerController.advance": { "total": 3355.8058921000224, "count": 63024, "self": 2.5802328000731904, "children": { "env_step": { "total": 1706.6492662999535, "count": 63024, "self": 1377.5888684999454, "children": { "SubprocessEnvManager._take_step": { "total": 327.46906000000337, "count": 63025, "self": 8.441055599959043, "children": { "TorchPolicy.evaluate": { "total": 319.0280044000443, "count": 62611, "self": 104.92986340007155, "children": { "TorchPolicy.sample_actions": { "total": 214.09814099997277, "count": 62611, "self": 214.09814099997277 } } } } }, "workers": { "total": 1.591337800004851, "count": 63024, "self": 0.0, "children": { "worker_root": { "total": 3346.181029500018, "count": 63024, "is_parallel": true, "self": 2157.7525975000017, "children": { "steps_from_proto": { "total": 0.003304900000000721, "count": 2, "is_parallel": true, "self": 0.0008608999999992761, "children": { "_process_rank_one_or_two_observation": { "total": 0.002444000000001445, "count": 16, "is_parallel": true, "self": 0.002444000000001445 } } }, "UnityEnvironment.step": { "total": 1188.4251271000164, "count": 63024, "is_parallel": true, "self": 34.4306848000208, "children": { "UnityEnvironment._generate_step_input": { "total": 27.589346599993707, "count": 63024, "is_parallel": true, "self": 27.589346599993707 }, "communicator.exchange": { "total": 1023.3885093000114, "count": 63024, "is_parallel": true, "self": 1023.3885093000114 }, "steps_from_proto": { "total": 103.0165863999904, "count": 63024, "is_parallel": true, "self": 28.484447699989104, "children": { "_process_rank_one_or_two_observation": { "total": 74.5321387000013, "count": 504192, "is_parallel": true, "self": 74.5321387000013 } } } } } } } } } } }, "trainer_advance": { "total": 1646.5763929999957, "count": 63024, "self": 3.765892799990752, "children": { "process_trajectory": { "total": 293.12345880000424, "count": 63024, "self": 292.754084600004, "children": { "RLTrainer._checkpoint": { "total": 0.3693742000002658, "count": 2, "self": 0.3693742000002658 } } }, "_update_policy": { "total": 1349.6870414000007, "count": 417, "self": 326.9591998999887, "children": { "TorchPPOOptimizer.update": { "total": 1022.727841500012, "count": 22980, "self": 1022.727841500012 } } } } } } }, "trainer_threads": { "total": 1.500000053056283e-06, "count": 1, "self": 1.500000053056283e-06 }, "TrainerController._save_models": { "total": 0.15406130000019402, "count": 1, "self": 0.010607400000026246, "children": { "RLTrainer._checkpoint": { "total": 0.14345390000016778, "count": 1, "self": 0.14345390000016778 } } } } } } }