{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6817441582679749, "min": 0.6812669038772583, "max": 1.4897942543029785, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 20343.24609375, "min": 20343.24609375, "max": 45194.3984375, "count": 33 }, "Pyramids.Step.mean": { "value": 989949.0, "min": 29952.0, "max": 989949.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989949.0, "min": 29952.0, "max": 989949.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.10966051369905472, "min": -0.24382281303405762, "max": 0.1638038456439972, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 27.30546760559082, "min": -57.786006927490234, "max": 40.78715896606445, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.010246028192341328, "min": -0.00287895230576396, "max": 0.43981707096099854, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.5512609481811523, "min": -0.7024643421173096, "max": 104.23664855957031, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07128216136230289, "min": 0.06560472116265303, "max": 0.07138339159396578, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9979502590722404, "min": 0.48128051985484743, "max": 1.0424460828265485, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.007567580394173828, "min": 0.00010834610483441862, "max": 0.009975991459195107, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.10594612551843359, "min": 0.001408499362847442, "max": 0.1496398718879266, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.250497583200003e-06, "min": 7.250497583200003e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010150696616480003, "min": 0.00010150696616480003, "max": 0.003381888272704, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10241680000000002, "min": 0.10241680000000002, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4338352000000003, "min": 1.3886848, "max": 2.5272960000000007, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025143832000000006, "min": 0.00025143832000000006, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003520136480000001, "min": 0.003520136480000001, "max": 0.11275687040000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008650797419250011, "min": 0.00832216627895832, "max": 0.27278968691825867, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12111116200685501, "min": 0.11651032418012619, "max": 1.9095278978347778, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 720.5, "min": 628.1304347826087, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31702.0, "min": 15984.0, "max": 32533.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.37011359886012296, "min": -1.0000000521540642, "max": 0.7073713965004399, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 16.28499834984541, "min": -31.996801659464836, "max": 31.099398605525494, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.37011359886012296, "min": -1.0000000521540642, "max": 0.7073713965004399, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 16.28499834984541, "min": -31.996801659464836, "max": 31.099398605525494, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06471653944853725, "min": 0.055592619776017156, "max": 5.189365650527179, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.847527735735639, "min": 2.557260509696789, "max": 83.02985040843487, "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": "1688362251", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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", "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": "1688364407" }, "total": 2155.9198765539995, "count": 1, "self": 0.5392404959998203, "children": { "run_training.setup": { "total": 0.04253433199983192, "count": 1, "self": 0.04253433199983192 }, "TrainerController.start_learning": { "total": 2155.338101726, "count": 1, "self": 1.514141946959171, "children": { "TrainerController._reset_env": { "total": 3.9068213789998936, "count": 1, "self": 3.9068213789998936 }, "TrainerController.advance": { "total": 2149.8201929540405, "count": 63235, "self": 1.5236326710760295, "children": { "env_step": { "total": 1504.2299138439676, "count": 63235, "self": 1383.919800572089, "children": { "SubprocessEnvManager._take_step": { "total": 119.39808784293928, "count": 63235, "self": 5.129962921911783, "children": { "TorchPolicy.evaluate": { "total": 114.26812492102749, "count": 62574, "self": 114.26812492102749 } } }, "workers": { "total": 0.912025428939387, "count": 63235, "self": 0.0, "children": { "worker_root": { "total": 2150.188888070964, "count": 63235, "is_parallel": true, "self": 887.2722736519313, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017572539998127468, "count": 1, "is_parallel": true, "self": 0.0005922020002344652, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011650519995782815, "count": 8, "is_parallel": true, "self": 0.0011650519995782815 } } }, "UnityEnvironment.step": { "total": 0.04948488700006237, "count": 1, "is_parallel": true, "self": 0.0005705720000150905, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005382570000165288, "count": 1, "is_parallel": true, "self": 0.0005382570000165288 }, "communicator.exchange": { "total": 0.04647717400007423, "count": 1, "is_parallel": true, "self": 0.04647717400007423 }, "steps_from_proto": { "total": 0.0018988839999565243, "count": 1, "is_parallel": true, "self": 0.0004021549998469709, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014967290001095535, "count": 8, "is_parallel": true, "self": 0.0014967290001095535 } } } } } } }, "UnityEnvironment.step": { "total": 1262.9166144190326, "count": 63234, "is_parallel": true, "self": 33.94804999100825, "children": { "UnityEnvironment._generate_step_input": { "total": 24.374183253981073, "count": 63234, "is_parallel": true, "self": 24.374183253981073 }, "communicator.exchange": { "total": 1095.6398001870214, "count": 63234, "is_parallel": true, "self": 1095.6398001870214 }, "steps_from_proto": { "total": 108.95458098702193, "count": 63234, "is_parallel": true, "self": 22.195607151042168, "children": { "_process_rank_one_or_two_observation": { "total": 86.75897383597976, "count": 505872, "is_parallel": true, "self": 86.75897383597976 } } } } } } } } } } }, "trainer_advance": { "total": 644.0666464389972, "count": 63235, "self": 2.7207698108859404, "children": { "process_trajectory": { "total": 113.42821745911328, "count": 63235, "self": 113.21540718011352, "children": { "RLTrainer._checkpoint": { "total": 0.21281027899976834, "count": 2, "self": 0.21281027899976834 } } }, "_update_policy": { "total": 527.917659168998, "count": 442, "self": 338.6875394830097, "children": { "TorchPPOOptimizer.update": { "total": 189.23011968598826, "count": 22830, "self": 189.23011968598826 } } } } } } }, "trainer_threads": { "total": 1.0220001058769412e-06, "count": 1, "self": 1.0220001058769412e-06 }, "TrainerController._save_models": { "total": 0.09694442399995751, "count": 1, "self": 0.0015278979999493458, "children": { "RLTrainer._checkpoint": { "total": 0.09541652600000816, "count": 1, "self": 0.09541652600000816 } } } } } } }