{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5466629266738892, "min": 0.5466629266738892, "max": 1.465348720550537, "count": 6 }, "Pyramids.Policy.Entropy.sum": { "value": 16775.9921875, "min": 16775.9921875, "max": 44452.8203125, "count": 6 }, "Pyramids.Step.mean": { "value": 179988.0, "min": 29952.0, "max": 179988.0, "count": 6 }, "Pyramids.Step.sum": { "value": 179988.0, "min": 29952.0, "max": 179988.0, "count": 6 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.07269908487796783, "min": -0.13288819789886475, "max": -0.016798747703433037, "count": 6 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -17.593177795410156, "min": -32.15894317626953, "max": -3.9813032150268555, "count": 6 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0847114846110344, "min": 0.0847114846110344, "max": 0.2949778735637665, "count": 6 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 20.500179290771484, "min": 20.500179290771484, "max": 71.3846435546875, "count": 6 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06808803357875416, "min": 0.06618938303697575, "max": 0.07409913934476829, "count": 6 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9532324701025583, "min": 0.518693975413378, "max": 0.9532324701025583, "count": 6 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.003840142381508174, "min": 0.00030370163568858974, "max": 0.02606736177440982, "count": 6 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.053761993341114436, "min": 0.003644419628263077, "max": 0.18247153242086875, "count": 6 }, "Pyramids.Policy.LearningRate.mean": { "value": 5.2588903898964275e-05, "min": 5.2588903898964275e-05, "max": 0.00027575315093942855, "count": 6 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0007362446545854999, "min": 0.0007362446545854999, "max": 0.0023202692265769996, "count": 6 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.11752960714285714, "min": 0.11752960714285714, "max": 0.19191771428571427, "count": 6 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.6454145, "min": 1.343424, "max": 1.9514420000000001, "count": 6 }, "Pyramids.Policy.Beta.mean": { "value": 0.0017612077535714284, "min": 0.0017612077535714284, "max": 0.009192579657142857, "count": 6 }, "Pyramids.Policy.Beta.sum": { "value": 0.02465690855, "min": 0.02465690855, "max": 0.0773649577, "count": 6 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.07023223489522934, "min": 0.07023223489522934, "max": 0.5150354504585266, "count": 6 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.9832512736320496, "min": 0.9453437924385071, "max": 3.605247974395752, "count": 6 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 920.8181818181819, "min": 920.8181818181819, "max": 999.0, "count": 6 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30387.0, "min": 15984.0, "max": 32871.0, "count": 6 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.45317063743577285, "min": -1.0000000521540642, "max": -0.45317063743577285, "count": 6 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -15.407801672816277, "min": -31.998401656746864, "max": -15.407801672816277, "count": 6 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.45317063743577285, "min": -1.0000000521540642, "max": -0.45317063743577285, "count": 6 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -15.407801672816277, "min": -31.998401656746864, "max": -15.407801672816277, "count": 6 }, "Pyramids.Policy.RndReward.mean": { "value": 0.6799053691108438, "min": 0.6799053691108438, "max": 11.266095484606922, "count": 6 }, "Pyramids.Policy.RndReward.sum": { "value": 23.116782549768686, "min": 23.116782549768686, "max": 180.25752775371075, "count": 6 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 6 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 6 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1793561497", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/content/mlagents-env/bin/mlagents-learn config/ppo/PyramidsRND.yaml --env=training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining --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": "1793562226" }, "total": 729.2421417509995, "count": 1, "self": 0.7427556679999725, "children": { "run_training.setup": { "total": 0.03843076099974496, "count": 1, "self": 0.03843076099974496 }, "TrainerController.start_learning": { "total": 728.4609553219998, "count": 1, "self": 0.4271389269970314, "children": { "TrainerController._reset_env": { "total": 5.248964276000152, "count": 1, "self": 5.248964276000152 }, "TrainerController.advance": { "total": 722.5216119270035, "count": 12561, "self": 0.4428161759756222, "children": { "env_step": { "total": 512.3416992329867, "count": 12561, "self": 479.9003781080364, "children": { "SubprocessEnvManager._take_step": { "total": 32.14875091401382, "count": 12561, "self": 1.3429957919920525, "children": { "TorchPolicy.evaluate": { "total": 30.805755122021765, "count": 12530, "self": 30.805755122021765 } } }, "workers": { "total": 0.29257021093644653, "count": 12561, "self": 0.0, "children": { "worker_root": { "total": 726.4814645580964, "count": 12561, "is_parallel": true, "self": 284.31975199003955, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0030985500002316257, "count": 1, "is_parallel": true, "self": 0.0011577260011108592, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019408239991207665, "count": 8, "is_parallel": true, "self": 0.0019408239991207665 } } }, "UnityEnvironment.step": { "total": 0.15782895499978622, "count": 1, "is_parallel": true, "self": 0.0007565779987999122, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005760790004387673, "count": 1, "is_parallel": true, "self": 0.0005760790004387673 }, "communicator.exchange": { "total": 0.15027561600027184, "count": 1, "is_parallel": true, "self": 0.15027561600027184 }, "steps_from_proto": { "total": 0.006220682000275701, "count": 1, "is_parallel": true, "self": 0.00043845800018971204, "children": { "_process_rank_one_or_two_observation": { "total": 0.005782224000085989, "count": 8, "is_parallel": true, "self": 0.005782224000085989 } } } } } } }, "UnityEnvironment.step": { "total": 442.1617125680568, "count": 12560, "is_parallel": true, "self": 10.479672651038527, "children": { "UnityEnvironment._generate_step_input": { "total": 6.753878799973336, "count": 12560, "is_parallel": true, "self": 6.753878799973336 }, "communicator.exchange": { "total": 393.21605879098524, "count": 12560, "is_parallel": true, "self": 393.21605879098524 }, "steps_from_proto": { "total": 31.71210232605972, "count": 12560, "is_parallel": true, "self": 6.325078872858285, "children": { "_process_rank_one_or_two_observation": { "total": 25.387023453201436, "count": 100480, "is_parallel": true, "self": 25.387023453201436 } } } } } } } } } } }, "trainer_advance": { "total": 209.7370965180412, "count": 12561, "self": 0.6371775760790115, "children": { "process_trajectory": { "total": 28.119897772958666, "count": 12561, "self": 28.119897772958666 }, "_update_policy": { "total": 180.98002116900352, "count": 74, "self": 72.01768132201005, "children": { "TorchPPOOptimizer.update": { "total": 108.96233984699347, "count": 4620, "self": 108.96233984699347 } } } } } } }, "trainer_threads": { "total": 1.6129997675307095e-06, "count": 1, "self": 1.6129997675307095e-06 }, "TrainerController._save_models": { "total": 0.263238578999335, "count": 1, "self": 0.0014270920000853948, "children": { "RLTrainer._checkpoint": { "total": 0.2618114869992496, "count": 1, "self": 0.2618114869992496 } } } } } } }