{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.551590085029602, "min": 0.551590085029602, "max": 1.577091097831726, "count": 50 }, "Pyramids.Policy.Entropy.sum": { "value": 10987.6748046875, "min": 10987.6748046875, "max": 31693.22265625, "count": 50 }, "Pyramids.Step.mean": { "value": 999996.0, "min": 19968.0, "max": 999996.0, "count": 50 }, "Pyramids.Step.sum": { "value": 999996.0, "min": 19968.0, "max": 999996.0, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5138071179389954, "min": -0.1796068400144577, "max": 0.5138071179389954, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 95.56812286376953, "min": -28.55748748779297, "max": 95.56812286376953, "count": 50 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.06619288772344589, "min": -0.0223530363291502, "max": 0.21983985602855682, "count": 50 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 12.311877250671387, "min": -3.9788405895233154, "max": 34.95453643798828, "count": 50 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06523274813338906, "min": 0.06457026638263078, "max": 0.07381447452698248, "count": 50 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.5870947332005015, "min": 0.29177958178822344, "max": 0.7300669412795161, "count": 50 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016980483297461265, "min": 0.0001669898494954476, "max": 0.017262498813107853, "count": 50 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1528243496771514, "min": 0.0013359187959635808, "max": 0.1607116995876947, "count": 50 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.939599020166669e-06, "min": 2.939599020166669e-06, "max": 0.0002969568010144, "count": 50 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.645639118150002e-05, "min": 2.645639118150002e-05, "max": 0.0022392214535929, "count": 50 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10097983333333334, "min": 0.10097983333333334, "max": 0.19898559999999998, "count": 50 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.9088185000000001, "min": 0.7959423999999999, "max": 1.7299627, "count": 50 }, "Pyramids.Policy.Beta.mean": { "value": 0.0001078853500000001, "min": 0.0001078853500000001, "max": 0.00989866144, "count": 50 }, "Pyramids.Policy.Beta.sum": { "value": 0.0009709681500000008, "min": 0.0009709681500000008, "max": 0.07465606929, "count": 50 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006949213799089193, "min": 0.006566396448761225, "max": 0.38224899768829346, "count": 50 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.06254292279481888, "min": 0.060324959456920624, "max": 1.5289959907531738, "count": 50 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 374.8474576271187, "min": 348.4807692307692, "max": 999.0, "count": 50 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 22116.0, "min": 15323.0, "max": 31968.0, "count": 50 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6222586012605964, "min": -1.0000000521540642, "max": 1.6222586012605964, "count": 50 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 94.09099887311459, "min": -32.000001668930054, "max": 94.09099887311459, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6222586012605964, "min": -1.0000000521540642, "max": 1.6222586012605964, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 94.09099887311459, "min": -32.000001668930054, "max": 94.09099887311459, "count": 50 }, "Pyramids.Policy.RndReward.mean": { "value": 0.026957215070006927, "min": 0.026129583753052948, "max": 5.808251433540136, "count": 50 }, "Pyramids.Policy.RndReward.sum": { "value": 1.5635184740604018, "min": 1.307538619497791, "max": 92.93202293664217, "count": 50 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1787394184", "python_version": "3.10.12 (main, Jul 26 2023, 13:20:36) [Clang 16.0.3 ]", "command_line_arguments": ".venv-mlagents/bin/mlagents-learn config/ppo/PyramidsRND.yaml --env=training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids1 --no-graphics --force", "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": "1787395087" }, "total": 903.479309686, "count": 1, "self": 0.5869812669999419, "children": { "run_training.setup": { "total": 0.0565203360000055, "count": 1, "self": 0.0565203360000055 }, "TrainerController.start_learning": { "total": 902.8358080830001, "count": 1, "self": 0.7708607759798269, "children": { "TrainerController._reset_env": { "total": 12.615482134000047, "count": 1, "self": 12.615482134000047 }, "TrainerController.advance": { "total": 889.3699326650202, "count": 63652, "self": 0.7434145150274389, "children": { "env_step": { "total": 536.1517973169932, "count": 63652, "self": 449.9551739180137, "children": { "SubprocessEnvManager._take_step": { "total": 85.70504401097747, "count": 63652, "self": 2.25659100996387, "children": { "TorchPolicy.evaluate": { "total": 83.4484530010136, "count": 62559, "self": 83.4484530010136 } } }, "workers": { "total": 0.4915793880020374, "count": 63652, "self": 0.0, "children": { "worker_root": { "total": 901.7233150899893, "count": 63652, "is_parallel": true, "self": 502.4046308449831, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.012606593999976212, "count": 1, "is_parallel": true, "self": 0.0021886170000016136, "children": { "_process_rank_one_or_two_observation": { "total": 0.010417976999974599, "count": 8, "is_parallel": true, "self": 0.010417976999974599 } } }, "UnityEnvironment.step": { "total": 0.031868248999955995, "count": 1, "is_parallel": true, "self": 0.00022133699997084477, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022066799999720388, "count": 1, "is_parallel": true, "self": 0.00022066799999720388 }, "communicator.exchange": { "total": 0.03067702699996744, "count": 1, "is_parallel": true, "self": 0.03067702699996744 }, "steps_from_proto": { "total": 0.0007492170000205078, "count": 1, "is_parallel": true, "self": 0.0001665239999510959, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005826930000694119, "count": 8, "is_parallel": true, "self": 0.0005826930000694119 } } } } } } }, "UnityEnvironment.step": { "total": 399.31868424500624, "count": 63651, "is_parallel": true, "self": 11.94500670706384, "children": { "UnityEnvironment._generate_step_input": { "total": 9.272525469963682, "count": 63651, "is_parallel": true, "self": 9.272525469963682 }, "communicator.exchange": { "total": 343.31836329697194, "count": 63651, "is_parallel": true, "self": 343.31836329697194 }, "steps_from_proto": { "total": 34.78278877100678, "count": 63651, "is_parallel": true, "self": 8.213779039975861, "children": { "_process_rank_one_or_two_observation": { "total": 26.569009731030917, "count": 509208, "is_parallel": true, "self": 26.569009731030917 } } } } } } } } } } }, "trainer_advance": { "total": 352.47472083299954, "count": 63652, "self": 1.356177588014532, "children": { "process_trajectory": { "total": 64.77816243298406, "count": 63652, "self": 62.96707069398411, "children": { "RLTrainer._checkpoint": { "total": 1.8110917389999486, "count": 10, "self": 1.8110917389999486 } } }, "_update_policy": { "total": 286.34038081200094, "count": 447, "self": 153.11913995300836, "children": { "TorchPPOOptimizer.update": { "total": 133.2212408589926, "count": 22818, "self": 133.2212408589926 } } } } } } }, "trainer_threads": { "total": 7.010000899754232e-07, "count": 1, "self": 7.010000899754232e-07 }, "TrainerController._save_models": { "total": 0.07953180699996665, "count": 1, "self": 0.0005698600000414444, "children": { "RLTrainer._checkpoint": { "total": 0.0789619469999252, "count": 1, "self": 0.0789619469999252 } } } } } } }