{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6306172013282776, "min": 0.6306172013282776, "max": 1.5000625848770142, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18787.34765625, "min": 18787.34765625, "max": 45505.8984375, "count": 33 }, "Pyramids.Step.mean": { "value": 989873.0, "min": 29952.0, "max": 989873.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989873.0, "min": 29952.0, "max": 989873.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2780269980430603, "min": -0.21987682580947876, "max": 0.30380329489707947, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 71.17491149902344, "min": -52.110809326171875, "max": 76.86223602294922, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 2.2964444160461426, "min": -0.4149775505065918, "max": 2.582235336303711, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 587.8897705078125, "min": -104.98931884765625, "max": 661.05224609375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07015124593453947, "min": 0.06527260835217828, "max": 0.07248724899268015, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9821174430835526, "min": 0.4866125142642018, "max": 1.0502036381318853, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.6435903009012244, "min": 0.0009816202030414583, "max": 1.0324237263573632, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 9.010264212617141, "min": 0.013742682842580418, "max": 14.453932169003085, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.415883242357143e-06, "min": 7.415883242357143e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.000103822365393, "min": 0.000103822365393, "max": 0.0036330400889866997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024719285714286, "min": 0.1024719285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346070000000004, "min": 1.3886848, "max": 2.6110133000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025694566428571434, "min": 0.00025694566428571434, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035972393000000004, "min": 0.0035972393000000004, "max": 0.12112022867000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014967844821512699, "min": 0.014967844821512699, "max": 0.5162975192070007, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20954982936382294, "min": 0.20954982936382294, "max": 3.6140825748443604, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 579.4150943396227, "min": 560.7872340425532, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30709.0, "min": 15984.0, "max": 32676.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.9676075172874162, "min": -1.0000000521540642, "max": 1.0550489568588686, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 51.28319841623306, "min": -30.707801662385464, "max": 52.312398709356785, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.9676075172874162, "min": -1.0000000521540642, "max": 1.0550489568588686, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 51.28319841623306, "min": -30.707801662385464, "max": 52.312398709356785, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.09097368387013392, "min": 0.09097368387013392, "max": 10.358347486704588, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.821605245117098, "min": 4.698557584662922, "max": 165.7335597872734, "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": "1753668341", "python_version": "3.10.12 (main, May 27 2025, 17:12:29) [GCC 11.4.0]", "command_line_arguments": "/content/myenv/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1753670066" }, "total": 1725.4835538589996, "count": 1, "self": 0.3257124899982955, "children": { "run_training.setup": { "total": 0.018147031000808056, "count": 1, "self": 0.018147031000808056 }, "TrainerController.start_learning": { "total": 1725.1396943380005, "count": 1, "self": 1.556689789956181, "children": { "TrainerController._reset_env": { "total": 2.3193654500000775, "count": 1, "self": 2.3193654500000775 }, "TrainerController.advance": { "total": 1721.180022991045, "count": 63475, "self": 1.4239351759633792, "children": { "env_step": { "total": 1072.3595206751415, "count": 63475, "self": 919.9929956020569, "children": { "SubprocessEnvManager._take_step": { "total": 151.49596102300256, "count": 63475, "self": 4.605746450050901, "children": { "TorchPolicy.evaluate": { "total": 146.89021457295166, "count": 62569, "self": 146.89021457295166 } } }, "workers": { "total": 0.8705640500820664, "count": 63475, "self": 0.0, "children": { "worker_root": { "total": 1722.773473471816, "count": 63475, "is_parallel": true, "self": 896.1209735206066, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023641690004296834, "count": 1, "is_parallel": true, "self": 0.000934569000492047, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014295999999376363, "count": 8, "is_parallel": true, "self": 0.0014295999999376363 } } }, "UnityEnvironment.step": { "total": 0.03853023900046537, "count": 1, "is_parallel": true, "self": 0.0003652159994089743, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00030341999990923796, "count": 1, "is_parallel": true, "self": 0.00030341999990923796 }, "communicator.exchange": { "total": 0.036787744000321254, "count": 1, "is_parallel": true, "self": 0.036787744000321254 }, "steps_from_proto": { "total": 0.0010738590008259052, "count": 1, "is_parallel": true, "self": 0.0002522370014048647, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008216219994210405, "count": 8, "is_parallel": true, "self": 0.0008216219994210405 } } } } } } }, "UnityEnvironment.step": { "total": 826.6524999512094, "count": 63474, "is_parallel": true, "self": 20.38005391222123, "children": { "UnityEnvironment._generate_step_input": { "total": 14.237620960053391, "count": 63474, "is_parallel": true, "self": 14.237620960053391 }, "communicator.exchange": { "total": 731.5227641769325, "count": 63474, "is_parallel": true, "self": 731.5227641769325 }, "steps_from_proto": { "total": 60.512060902002304, "count": 63474, "is_parallel": true, "self": 13.132761611647766, "children": { "_process_rank_one_or_two_observation": { "total": 47.37929929035454, "count": 507792, "is_parallel": true, "self": 47.37929929035454 } } } } } } } } } } }, "trainer_advance": { "total": 647.3965671399401, "count": 63475, "self": 2.942783846905513, "children": { "process_trajectory": { "total": 122.77681901502638, "count": 63475, "self": 122.5743966360269, "children": { "RLTrainer._checkpoint": { "total": 0.20242237899947213, "count": 2, "self": 0.20242237899947213 } } }, "_update_policy": { "total": 521.6769642780082, "count": 450, "self": 284.2131316989762, "children": { "TorchPPOOptimizer.update": { "total": 237.463832579032, "count": 22803, "self": 237.463832579032 } } } } } } }, "trainer_threads": { "total": 9.389996193931438e-07, "count": 1, "self": 9.389996193931438e-07 }, "TrainerController._save_models": { "total": 0.08361516799959645, "count": 1, "self": 0.001187747999210842, "children": { "RLTrainer._checkpoint": { "total": 0.08242742000038561, "count": 1, "self": 0.08242742000038561 } } } } } } }