{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4531543254852295, "min": 0.4531543254852295, "max": 1.0132265090942383, "count": 17 }, "Pyramids.Policy.Entropy.sum": { "value": 13427.869140625, "min": 10796.94140625, "max": 30436.46875, "count": 17 }, "Pyramids.Step.mean": { "value": 989961.0, "min": 509993.0, "max": 989961.0, "count": 17 }, "Pyramids.Step.sum": { "value": 989961.0, "min": 509993.0, "max": 989961.0, "count": 17 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.314156711101532, "min": -0.020626777783036232, "max": 0.3798234164714813, "count": 17 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 82.3090591430664, "min": -1.6707689762115479, "max": 98.75408935546875, "count": 17 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.033712223172187805, "min": -0.033712223172187805, "max": 0.04274001717567444, "count": 17 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -8.832602500915527, "min": -8.832602500915527, "max": 11.069664001464844, "count": 17 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 486.42622950819674, "min": 309.25, "max": 834.025641025641, "count": 17 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29672.0, "min": 1237.0, "max": 32696.0, "count": 17 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.1856098056572382, "min": -0.11661030103762944, "max": 1.690750002861023, "count": 17 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 72.32219814509153, "min": -4.547801740467548, "max": 83.06279814988375, "count": 17 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.1856098056572382, "min": -0.11661030103762944, "max": 1.690750002861023, "count": 17 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 72.32219814509153, "min": -4.547801740467548, "max": 83.06279814988375, "count": 17 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06454847306852825, "min": 0.051007845118874684, "max": 0.12605790901579894, "count": 17 }, "Pyramids.Policy.RndReward.sum": { "value": 3.937456857180223, "min": 0.20403138047549874, "max": 5.042316360631958, "count": 17 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06812104680284393, "min": 0.06629444303351203, "max": 0.07307606635534865, "count": 17 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.953694655239815, "min": 0.2923042654213946, "max": 1.0957097937838018, "count": 17 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013116745470878889, "min": 0.0026308059390371535, "max": 0.014184579108890222, "count": 17 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18363443659230444, "min": 0.010523223756148614, "max": 0.19858410752446312, "count": 17 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.550047483350001e-06, "min": 7.550047483350001e-06, "max": 0.00014832387555872498, "count": 17 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010570066476690001, "min": 0.00010570066476690001, "max": 0.0018691090769639, "count": 17 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251664999999999, "min": 0.10251664999999999, "max": 0.14944127500000004, "count": 17 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352330999999998, "min": 0.5977651000000002, "max": 2.0230361000000006, "count": 17 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026141333500000007, "min": 0.00026141333500000007, "max": 0.0049491833725, "count": 17 }, "Pyramids.Policy.Beta.sum": { "value": 0.003659786690000001, "min": 0.003659786690000001, "max": 0.06238130639, "count": 17 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012849760241806507, "min": 0.011811994947493076, "max": 0.015293809585273266, "count": 17 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17989663779735565, "min": 0.05437934026122093, "max": 0.21411333978176117, "count": 17 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 17 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 17 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1694541431", "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\bdonn\\miniconda3\\envs\\DRL\\Scripts\\mlagents-learn ./config/ppo/PyramidsRND.yaml --env=../Pyramids/UnityEnvironment.exe --run-id=Pyramids Training --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1", "numpy_version": "1.25.2", "end_time_seconds": "1694542605" }, "total": 1173.3677240000106, "count": 1, "self": 0.3613532001618296, "children": { "run_training.setup": { "total": 0.17205539997667074, "count": 1, "self": 0.17205539997667074 }, "TrainerController.start_learning": { "total": 1172.8343153998721, "count": 1, "self": 1.0854164024349302, "children": { "TrainerController._reset_env": { "total": 6.197830699849874, "count": 1, "self": 6.197830699849874 }, "TrainerController.advance": { "total": 1165.4142691974994, "count": 31986, "self": 0.9317487992811948, "children": { "env_step": { "total": 654.2052320900839, "count": 31986, "self": 524.4149543903768, "children": { "SubprocessEnvManager._take_step": { "total": 129.08072021254338, "count": 31986, "self": 2.8359906140249223, "children": { "TorchPolicy.evaluate": { "total": 126.24472959851846, "count": 31312, "self": 126.24472959851846 } } }, "workers": { "total": 0.7095574871636927, "count": 31986, "self": 0.0, "children": { "worker_root": { "total": 1166.8321079106536, "count": 31986, "is_parallel": true, "self": 713.9999165155459, "children": { "steps_from_proto": { "total": 0.0012974001001566648, "count": 1, "is_parallel": true, "self": 0.0003544003702700138, "children": { "_process_rank_one_or_two_observation": { "total": 0.000942999729886651, "count": 8, "is_parallel": true, "self": 0.000942999729886651 } } }, "UnityEnvironment.step": { "total": 452.8308939950075, "count": 31986, "is_parallel": true, "self": 11.983218401670456, "children": { "UnityEnvironment._generate_step_input": { "total": 9.725233814446256, "count": 31986, "is_parallel": true, "self": 9.725233814446256 }, "communicator.exchange": { "total": 396.8172612024937, "count": 31986, "is_parallel": true, "self": 396.8172612024937 }, "steps_from_proto": { "total": 34.305180576397106, "count": 31986, "is_parallel": true, "self": 7.4639062327332795, "children": { "_process_rank_one_or_two_observation": { "total": 26.841274343663827, "count": 255888, "is_parallel": true, "self": 26.841274343663827 } } } } } } } } } } }, "trainer_advance": { "total": 510.2772883081343, "count": 31986, "self": 2.3398887978401035, "children": { "process_trajectory": { "total": 98.11965311155654, "count": 31986, "self": 97.80131631135009, "children": { "RLTrainer._checkpoint": { "total": 0.3183368002064526, "count": 2, "self": 0.3183368002064526 } } }, "_update_policy": { "total": 409.81774639873765, "count": 234, "self": 222.75601530075073, "children": { "TorchPPOOptimizer.update": { "total": 187.06173109798692, "count": 11346, "self": 187.06173109798692 } } } } } } }, "trainer_threads": { "total": 1.00000761449337e-06, "count": 1, "self": 1.00000761449337e-06 }, "TrainerController._save_models": { "total": 0.1367981000803411, "count": 1, "self": 0.016386400209739804, "children": { "RLTrainer._checkpoint": { "total": 0.1204116998706013, "count": 1, "self": 0.1204116998706013 } } } } } } }