{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.672910749912262, "min": 0.616730809211731, "max": 1.4508994817733765, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 20273.455078125, "min": 18472.3203125, "max": 44014.48828125, "count": 33 }, "Pyramids.Step.mean": { "value": 989987.0, "min": 29952.0, "max": 989987.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989987.0, "min": 29952.0, "max": 989987.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.10608898848295212, "min": -0.11718977242708206, "max": 0.1571715921163559, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 26.310070037841797, "min": -28.35992431640625, "max": 39.450069427490234, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.045009151101112366, "min": -0.045009151101112366, "max": 0.37586790323257446, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -11.162269592285156, "min": -11.162269592285156, "max": 89.08069610595703, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07146338403464242, "min": 0.06506722529314171, "max": 0.07281231384518187, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0719507605196363, "min": 0.48680259599412284, "max": 1.0719507605196363, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.007467172420810028, "min": 0.00030027468442815966, "max": 0.012326708114456759, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.11200758631215041, "min": 0.003603296213137916, "max": 0.12927786844314443, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.466857511080003e-06, "min": 7.466857511080003e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011200286266620005, "min": 0.00011200286266620005, "max": 0.0032564720145094, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248892000000001, "min": 0.10248892000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5373338, "min": 1.3691136000000002, "max": 2.4012773, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025864310800000013, "min": 0.00025864310800000013, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003879646620000002, "min": 0.003879646620000002, "max": 0.10857051094, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01378475409001112, "min": 0.01378475409001112, "max": 0.5093545317649841, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20677131414413452, "min": 0.19732972979545593, "max": 3.565481662750244, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 775.7777777777778, "min": 685.3636363636364, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27928.0, "min": 15984.0, "max": 32535.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.2795332939260536, "min": -1.0000000521540642, "max": 0.6325863267887722, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 10.063198581337929, "min": -32.000001668930054, "max": 27.83379837870598, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.2795332939260536, "min": -1.0000000521540642, "max": 0.6325863267887722, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 10.063198581337929, "min": -32.000001668930054, "max": 27.83379837870598, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.10934112376869759, "min": 0.10086687872436331, "max": 10.808986278250813, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.9362804556731135, "min": 3.9362804556731135, "max": 172.94378045201302, "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": "1684687578", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "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 --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1684689398" }, "total": 1820.4243316379998, "count": 1, "self": 0.3728432879997854, "children": { "run_training.setup": { "total": 0.04471152600035566, "count": 1, "self": 0.04471152600035566 }, "TrainerController.start_learning": { "total": 1820.0067768239996, "count": 1, "self": 1.7925489049684984, "children": { "TrainerController._reset_env": { "total": 0.8317693110002438, "count": 1, "self": 0.8317693110002438 }, "TrainerController.advance": { "total": 1817.2865952210313, "count": 63199, "self": 1.697485334963858, "children": { "env_step": { "total": 1146.9654740730366, "count": 63199, "self": 1052.0796794200733, "children": { "SubprocessEnvManager._take_step": { "total": 93.80180647793804, "count": 63199, "self": 5.2984733749590305, "children": { "TorchPolicy.evaluate": { "total": 88.50333310297901, "count": 62561, "self": 88.50333310297901 } } }, "workers": { "total": 1.083988175025297, "count": 63199, "self": 0.0, "children": { "worker_root": { "total": 1817.090095374011, "count": 63199, "is_parallel": true, "self": 877.0513256671402, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019190610000805464, "count": 1, "is_parallel": true, "self": 0.000591429001360666, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013276319987198804, "count": 8, "is_parallel": true, "self": 0.0013276319987198804 } } }, "UnityEnvironment.step": { "total": 0.04031272300017008, "count": 1, "is_parallel": true, "self": 0.00038763000065955566, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00031544099965685746, "count": 1, "is_parallel": true, "self": 0.00031544099965685746 }, "communicator.exchange": { "total": 0.03832684400003927, "count": 1, "is_parallel": true, "self": 0.03832684400003927 }, "steps_from_proto": { "total": 0.0012828079998143949, "count": 1, "is_parallel": true, "self": 0.0002744330004134099, "children": { "_process_rank_one_or_two_observation": { "total": 0.001008374999400985, "count": 8, "is_parallel": true, "self": 0.001008374999400985 } } } } } } }, "UnityEnvironment.step": { "total": 940.0387697068709, "count": 63198, "is_parallel": true, "self": 23.774064885807093, "children": { "UnityEnvironment._generate_step_input": { "total": 15.930998650875154, "count": 63198, "is_parallel": true, "self": 15.930998650875154 }, "communicator.exchange": { "total": 831.672887262016, "count": 63198, "is_parallel": true, "self": 831.672887262016 }, "steps_from_proto": { "total": 68.66081890817259, "count": 63198, "is_parallel": true, "self": 14.91194012800861, "children": { "_process_rank_one_or_two_observation": { "total": 53.74887878016398, "count": 505584, "is_parallel": true, "self": 53.74887878016398 } } } } } } } } } } }, "trainer_advance": { "total": 668.6236358130309, "count": 63199, "self": 3.090019102070073, "children": { "process_trajectory": { "total": 100.1443645399695, "count": 63199, "self": 99.9334961989698, "children": { "RLTrainer._checkpoint": { "total": 0.21086834099969565, "count": 2, "self": 0.21086834099969565 } } }, "_update_policy": { "total": 565.3892521709913, "count": 442, "self": 323.4010258780281, "children": { "TorchPPOOptimizer.update": { "total": 241.9882262929632, "count": 22773, "self": 241.9882262929632 } } } } } } }, "trainer_threads": { "total": 1.4170000213198364e-06, "count": 1, "self": 1.4170000213198364e-06 }, "TrainerController._save_models": { "total": 0.09586196999953245, "count": 1, "self": 0.0018641520000528544, "children": { "RLTrainer._checkpoint": { "total": 0.0939978179994796, "count": 1, "self": 0.0939978179994796 } } } } } } }