{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.41078394651412964, "min": 0.4095400869846344, "max": 1.3696956634521484, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12251.220703125, "min": 12220.67578125, "max": 41551.0859375, "count": 33 }, "Pyramids.Step.mean": { "value": 989976.0, "min": 29945.0, "max": 989976.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989976.0, "min": 29945.0, "max": 989976.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.35433879494667053, "min": -0.09399523586034775, "max": 0.37853771448135376, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 92.83676147460938, "min": -22.652851104736328, "max": 99.555419921875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.003528849920257926, "min": -0.03828004375100136, "max": 0.4169260263442993, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.924558699131012, "min": -9.646571159362793, "max": 98.81147003173828, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07130675445798608, "min": 0.063502892873089, "max": 0.0733289213507718, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.998294562411805, "min": 0.5021237960530528, "max": 1.0283784134565697, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016220093043687354, "min": 0.0014942152583671184, "max": 0.017930829031480165, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22708130261162293, "min": 0.016466219898067392, "max": 0.2510316064407223, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.540833200707147e-06, "min": 7.540833200707147e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010557166480990007, "min": 0.00010557166480990007, "max": 0.0036324283891905995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251357857142859, "min": 0.10251357857142859, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351901000000002, "min": 1.3886848, "max": 2.610809400000001, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002611064992857145, "min": 0.0002611064992857145, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036554909900000025, "min": 0.0036554909900000025, "max": 0.12109985906000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012091363780200481, "min": 0.012091363780200481, "max": 0.4375329911708832, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1692790985107422, "min": 0.1692790985107422, "max": 3.0627310276031494, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 464.0983606557377, "min": 453.95588235294116, "max": 992.4705882352941, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28310.0, "min": 16872.0, "max": 32589.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.371921287208307, "min": -0.9280968265187356, "max": 1.4577852651915129, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 83.68719851970673, "min": -30.619401656091213, "max": 99.12939803302288, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.371921287208307, "min": -0.9280968265187356, "max": 1.4577852651915129, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 83.68719851970673, "min": -30.619401656091213, "max": 99.12939803302288, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05894064438122813, "min": 0.058526371393193534, "max": 8.54708165456267, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.595379307254916, "min": 3.595379307254916, "max": 145.30038812756538, "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": "1690549358", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "1690551676" }, "total": 2317.955381923, "count": 1, "self": 0.7924951890004195, "children": { "run_training.setup": { "total": 0.05377989099997649, "count": 1, "self": 0.05377989099997649 }, "TrainerController.start_learning": { "total": 2317.1091068429996, "count": 1, "self": 1.598196981030469, "children": { "TrainerController._reset_env": { "total": 4.691545566000059, "count": 1, "self": 4.691545566000059 }, "TrainerController.advance": { "total": 2310.661099816969, "count": 63567, "self": 1.58558431892925, "children": { "env_step": { "total": 1618.1647922400575, "count": 63567, "self": 1495.8991322170702, "children": { "SubprocessEnvManager._take_step": { "total": 121.30193584504696, "count": 63567, "self": 5.259968947023026, "children": { "TorchPolicy.evaluate": { "total": 116.04196689802393, "count": 62552, "self": 116.04196689802393 } } }, "workers": { "total": 0.9637241779403212, "count": 63567, "self": 0.0, "children": { "worker_root": { "total": 2311.181558830086, "count": 63567, "is_parallel": true, "self": 944.0419506230501, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0027037289999043423, "count": 1, "is_parallel": true, "self": 0.0008107259995995264, "children": { "_process_rank_one_or_two_observation": { "total": 0.001893003000304816, "count": 8, "is_parallel": true, "self": 0.001893003000304816 } } }, "UnityEnvironment.step": { "total": 0.0493866120000348, "count": 1, "is_parallel": true, "self": 0.0006584220002423535, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004785950000041339, "count": 1, "is_parallel": true, "self": 0.0004785950000041339 }, "communicator.exchange": { "total": 0.04646213999990323, "count": 1, "is_parallel": true, "self": 0.04646213999990323 }, "steps_from_proto": { "total": 0.0017874549998850853, "count": 1, "is_parallel": true, "self": 0.00036026699945068685, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014271880004343984, "count": 8, "is_parallel": true, "self": 0.0014271880004343984 } } } } } } }, "UnityEnvironment.step": { "total": 1367.139608207036, "count": 63566, "is_parallel": true, "self": 36.90651828203204, "children": { "UnityEnvironment._generate_step_input": { "total": 25.64739327100051, "count": 63566, "is_parallel": true, "self": 25.64739327100051 }, "communicator.exchange": { "total": 1190.1476048189675, "count": 63566, "is_parallel": true, "self": 1190.1476048189675 }, "steps_from_proto": { "total": 114.43809183503595, "count": 63566, "is_parallel": true, "self": 23.783321238078088, "children": { "_process_rank_one_or_two_observation": { "total": 90.65477059695786, "count": 508528, "is_parallel": true, "self": 90.65477059695786 } } } } } } } } } } }, "trainer_advance": { "total": 690.9107232579825, "count": 63567, "self": 2.9840141529971334, "children": { "process_trajectory": { "total": 121.65125984698489, "count": 63567, "self": 121.35381263698491, "children": { "RLTrainer._checkpoint": { "total": 0.297447209999973, "count": 2, "self": 0.297447209999973 } } }, "_update_policy": { "total": 566.2754492580004, "count": 454, "self": 369.67502843899206, "children": { "TorchPPOOptimizer.update": { "total": 196.60042081900838, "count": 22788, "self": 196.60042081900838 } } } } } } }, "trainer_threads": { "total": 1.488000179961091e-06, "count": 1, "self": 1.488000179961091e-06 }, "TrainerController._save_models": { "total": 0.15826299099990138, "count": 1, "self": 0.0020084130001123413, "children": { "RLTrainer._checkpoint": { "total": 0.15625457799978903, "count": 1, "self": 0.15625457799978903 } } } } } } }