{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.426729291677475, "min": 0.4204860031604767, "max": 1.4439810514450073, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12713.119140625, "min": 12580.94140625, "max": 43804.609375, "count": 33 }, "Pyramids.Step.mean": { "value": 989973.0, "min": 29977.0, "max": 989973.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989973.0, "min": 29977.0, "max": 989973.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5085303783416748, "min": -0.09351290762424469, "max": 0.5877529382705688, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 141.37144470214844, "min": -22.443098068237305, "max": 165.1585693359375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0065453797578811646, "min": 0.001932007959112525, "max": 0.19621361792087555, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.8196156024932861, "min": 0.5428942441940308, "max": 47.28748321533203, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.068181490521038, "min": 0.06522663136378729, "max": 0.07273073442047462, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.02272235781557, "min": 0.4908087179158418, "max": 1.0684806649029874, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016726049549955255, "min": 0.0008761706070791006, "max": 0.01744776185307569, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2508907432493288, "min": 0.011390217892028308, "max": 0.2508907432493288, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.53893748705333e-06, "min": 7.53893748705333e-06, "max": 0.00029523733015898577, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011308406230579995, "min": 0.00011308406230579995, "max": 0.0034919002360332993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025129466666667, "min": 0.1025129466666667, "max": 0.19841244285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5376942000000005, "min": 1.3888871, "max": 2.4859437000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026104337199999995, "min": 0.00026104337199999995, "max": 0.009841403041428571, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003915650579999999, "min": 0.003915650579999999, "max": 0.11641027333000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01116347499191761, "min": 0.010985763743519783, "max": 0.3874010741710663, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1674521267414093, "min": 0.15380069613456726, "max": 2.7118074893951416, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 350.0235294117647, "min": 339.0568181818182, "max": 988.9230769230769, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29752.0, "min": 16520.0, "max": 32724.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5558282202657532, "min": -0.925248534841971, "max": 1.5728487609544906, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 132.24539872258902, "min": -30.533201649785042, "max": 139.24919794499874, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5558282202657532, "min": -0.925248534841971, "max": 1.5728487609544906, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 132.24539872258902, "min": -30.533201649785042, "max": 139.24919794499874, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.040781866184860356, "min": 0.04020544079863208, "max": 7.275505214272177, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.4664586257131305, "min": 3.3659271099968464, "max": 123.683588642627, "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": "1741644590", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training2 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1741646797" }, "total": 2207.237673422, "count": 1, "self": 0.48640223599977617, "children": { "run_training.setup": { "total": 0.019774184000198147, "count": 1, "self": 0.019774184000198147 }, "TrainerController.start_learning": { "total": 2206.731497002, "count": 1, "self": 1.4023000119341305, "children": { "TrainerController._reset_env": { "total": 2.1694649689998187, "count": 1, "self": 2.1694649689998187 }, "TrainerController.advance": { "total": 2203.0604636340663, "count": 63854, "self": 1.4560458570613264, "children": { "env_step": { "total": 1519.6183184240185, "count": 63854, "self": 1362.1397403710034, "children": { "SubprocessEnvManager._take_step": { "total": 156.68204770498596, "count": 63854, "self": 4.729656439965311, "children": { "TorchPolicy.evaluate": { "total": 151.95239126502065, "count": 62548, "self": 151.95239126502065 } } }, "workers": { "total": 0.7965303480291368, "count": 63854, "self": 0.0, "children": { "worker_root": { "total": 2201.5888796640393, "count": 63854, "is_parallel": true, "self": 955.0277293460122, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020011130000057165, "count": 1, "is_parallel": true, "self": 0.0006740120002177719, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013271009997879446, "count": 8, "is_parallel": true, "self": 0.0013271009997879446 } } }, "UnityEnvironment.step": { "total": 0.05232477200024732, "count": 1, "is_parallel": true, "self": 0.0005824680006298877, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005143429998497595, "count": 1, "is_parallel": true, "self": 0.0005143429998497595 }, "communicator.exchange": { "total": 0.049548999999842636, "count": 1, "is_parallel": true, "self": 0.049548999999842636 }, "steps_from_proto": { "total": 0.0016789609999250388, "count": 1, "is_parallel": true, "self": 0.00035793099868897116, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013210300012360676, "count": 8, "is_parallel": true, "self": 0.0013210300012360676 } } } } } } }, "UnityEnvironment.step": { "total": 1246.561150318027, "count": 63853, "is_parallel": true, "self": 32.29060810508872, "children": { "UnityEnvironment._generate_step_input": { "total": 23.78701599191436, "count": 63853, "is_parallel": true, "self": 23.78701599191436 }, "communicator.exchange": { "total": 1092.1735659889891, "count": 63853, "is_parallel": true, "self": 1092.1735659889891 }, "steps_from_proto": { "total": 98.30996023203488, "count": 63853, "is_parallel": true, "self": 19.931568536209852, "children": { "_process_rank_one_or_two_observation": { "total": 78.37839169582503, "count": 510824, "is_parallel": true, "self": 78.37839169582503 } } } } } } } } } } }, "trainer_advance": { "total": 681.9860993529865, "count": 63854, "self": 2.7191261249317904, "children": { "process_trajectory": { "total": 129.44218922405753, "count": 63854, "self": 129.23136131205774, "children": { "RLTrainer._checkpoint": { "total": 0.210827911999786, "count": 2, "self": 0.210827911999786 } } }, "_update_policy": { "total": 549.8247840039971, "count": 452, "self": 301.3812571300009, "children": { "TorchPPOOptimizer.update": { "total": 248.44352687399623, "count": 22761, "self": 248.44352687399623 } } } } } } }, "trainer_threads": { "total": 9.920004231389612e-07, "count": 1, "self": 9.920004231389612e-07 }, "TrainerController._save_models": { "total": 0.09926739499951509, "count": 1, "self": 0.001566295999509748, "children": { "RLTrainer._checkpoint": { "total": 0.09770109900000534, "count": 1, "self": 0.09770109900000534 } } } } } } }