{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.8603444695472717, "min": 0.7730680704116821, "max": 1.3796371221542358, "count": 34 }, "Pyramids.Policy.Entropy.sum": { "value": 25989.28515625, "min": 23142.56640625, "max": 41852.671875, "count": 34 }, "Pyramids.Step.mean": { "value": 1019973.0, "min": 29952.0, "max": 1019973.0, "count": 34 }, "Pyramids.Step.sum": { "value": 1019973.0, "min": 29952.0, "max": 1019973.0, "count": 34 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.04519736394286156, "min": -0.14918752014636993, "max": 0.06724056601524353, "count": 34 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 11.208946228027344, "min": -35.35744094848633, "max": 16.541179656982422, "count": 34 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.017207594588398933, "min": 0.010886333882808685, "max": 0.43173322081565857, "count": 34 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.267483234405518, "min": 2.634492874145508, "max": 102.32077026367188, "count": 34 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06897612204184986, "min": 0.06421214065494595, "max": 0.07144335827987863, "count": 34 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.965665708585898, "min": 0.4911759309499088, "max": 1.0196657982693675, "count": 34 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0038745900391451075, "min": 5.431613643717974e-05, "max": 0.010480514626616286, "count": 34 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.054244260548031505, "min": 0.0007061097736833366, "max": 0.07336360238631401, "count": 34 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00014927123238579643, "min": 0.00014927123238579643, "max": 0.0002975753150939428, "count": 34 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00208979725340115, "min": 0.0020536704154432, "max": 0.0034123549125484503, "count": 34 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.14975706071428574, "min": 0.14975706071428574, "max": 0.19919177142857142, "count": 34 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.0965988500000003, "min": 1.3845568000000001, "max": 2.5374515500000006, "count": 34 }, "Pyramids.Policy.Beta.mean": { "value": 0.004980730365357143, "min": 0.004980730365357143, "max": 0.009919257965714285, "count": 34 }, "Pyramids.Policy.Beta.sum": { "value": 0.069730225115, "min": 0.06845722432, "max": 0.113771409845, "count": 34 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009898989461362362, "min": 0.009898989461362362, "max": 0.5906906723976135, "count": 34 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13858585059642792, "min": 0.13858585059642792, "max": 4.1348347663879395, "count": 34 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 852.0, "min": 833.4117647058823, "max": 999.0, "count": 34 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30672.0, "min": 15984.0, "max": 32880.0, "count": 34 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.09954599129992563, "min": -1.0000000521540642, "max": -0.07053337391051981, "count": 34 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -3.683201678097248, "min": -32.000001668930054, "max": -2.5392014607787132, "count": 34 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.09954599129992563, "min": -1.0000000521540642, "max": -0.07053337391051981, "count": 34 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -3.683201678097248, "min": -32.000001668930054, "max": -2.5392014607787132, "count": 34 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08957059873972793, "min": 0.08957059873972793, "max": 12.816517071798444, "count": 34 }, "Pyramids.Policy.RndReward.sum": { "value": 3.3141121533699334, "min": 3.1070871035335585, "max": 205.0642731487751, "count": 34 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 34 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 34 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1778580199", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1778582474" }, "total": 2274.589055964, "count": 1, "self": 0.36067582800023956, "children": { "run_training.setup": { "total": 0.024072522000096797, "count": 1, "self": 0.024072522000096797 }, "TrainerController.start_learning": { "total": 2274.204307614, "count": 1, "self": 1.4176380080580202, "children": { "TrainerController._reset_env": { "total": 2.2082828279999376, "count": 1, "self": 2.2082828279999376 }, "TrainerController.advance": { "total": 2270.454977177941, "count": 65515, "self": 1.5419593057886232, "children": { "env_step": { "total": 1581.875819892236, "count": 65515, "self": 1418.4264207463048, "children": { "SubprocessEnvManager._take_step": { "total": 162.6024345229116, "count": 65515, "self": 4.842090668008495, "children": { "TorchPolicy.evaluate": { "total": 157.7603438549031, "count": 64922, "self": 157.7603438549031 } } }, "workers": { "total": 0.8469646230196304, "count": 65515, "self": 0.0, "children": { "worker_root": { "total": 2268.007274864187, "count": 65515, "is_parallel": true, "self": 970.864565665106, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019566330001907772, "count": 1, "is_parallel": true, "self": 0.0006139659990367363, "children": { "_process_rank_one_or_two_observation": { "total": 0.001342667001154041, "count": 8, "is_parallel": true, "self": 0.001342667001154041 } } }, "UnityEnvironment.step": { "total": 0.07818546500038792, "count": 1, "is_parallel": true, "self": 0.0005425520002972917, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004626700001608697, "count": 1, "is_parallel": true, "self": 0.0004626700001608697 }, "communicator.exchange": { "total": 0.07515730100021756, "count": 1, "is_parallel": true, "self": 0.07515730100021756 }, "steps_from_proto": { "total": 0.0020229419997122022, "count": 1, "is_parallel": true, "self": 0.0004387320004752837, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015842099992369185, "count": 8, "is_parallel": true, "self": 0.0015842099992369185 } } } } } } }, "UnityEnvironment.step": { "total": 1297.1427091990809, "count": 65514, "is_parallel": true, "self": 35.56836148214916, "children": { "UnityEnvironment._generate_step_input": { "total": 24.673139709926545, "count": 65514, "is_parallel": true, "self": 24.673139709926545 }, "communicator.exchange": { "total": 1122.262845511138, "count": 65514, "is_parallel": true, "self": 1122.262845511138 }, "steps_from_proto": { "total": 114.63836249586711, "count": 65514, "is_parallel": true, "self": 23.894419243061748, "children": { "_process_rank_one_or_two_observation": { "total": 90.74394325280537, "count": 524112, "is_parallel": true, "self": 90.74394325280537 } } } } } } } } } } }, "trainer_advance": { "total": 687.0371979799165, "count": 65515, "self": 2.5015827357801754, "children": { "process_trajectory": { "total": 124.47239245114179, "count": 65515, "self": 124.14678105514213, "children": { "RLTrainer._checkpoint": { "total": 0.32561139599965827, "count": 2, "self": 0.32561139599965827 } } }, "_update_policy": { "total": 560.0632227929946, "count": 449, "self": 309.14290617600363, "children": { "TorchPPOOptimizer.update": { "total": 250.92031661699093, "count": 23710, "self": 250.92031661699093 } } } } } } }, "trainer_threads": { "total": 1.4300003385869786e-06, "count": 1, "self": 1.4300003385869786e-06 }, "TrainerController._save_models": { "total": 0.1234081700004026, "count": 1, "self": 0.0012929329996040906, "children": { "RLTrainer._checkpoint": { "total": 0.12211523700079852, "count": 1, "self": 0.12211523700079852 } } } } } } }