{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3555440604686737, "min": 0.3444250524044037, "max": 1.4453279972076416, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10654.9443359375, "min": 10277.6435546875, "max": 43845.46875, "count": 33 }, "Pyramids.Step.mean": { "value": 989936.0, "min": 29884.0, "max": 989936.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989936.0, "min": 29884.0, "max": 989936.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7168408632278442, "min": -0.11632892489433289, "max": 0.7337176203727722, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 207.88385009765625, "min": -28.03527069091797, "max": 220.8489990234375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.005016577895730734, "min": -0.01984540745615959, "max": 0.32494187355041504, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.4548076391220093, "min": -5.556714057922363, "max": 78.31098937988281, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06983554277255842, "min": 0.065082382624906, "max": 0.07398626746989136, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.977697598815818, "min": 0.5689214679210824, "max": 1.0662160731250576, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016041410039179024, "min": 0.0008615226076904601, "max": 0.01746883107512649, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22457974054850635, "min": 0.010338271292285522, "max": 0.2555410061171392, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.440461805592858e-06, "min": 7.440461805592858e-06, "max": 0.0002947688642437125, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010416646527830001, "min": 0.00010416646527830001, "max": 0.0036327196890934997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248012142857144, "min": 0.10248012142857144, "max": 0.1982562875, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347217, "min": 1.4347217, "max": 2.6109065000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025776413071428576, "min": 0.00025776413071428576, "max": 0.00982580312125, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036086978300000007, "min": 0.0036086978300000007, "max": 0.12110955934999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01404791884124279, "min": 0.01404791884124279, "max": 0.4897589087486267, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19667086005210876, "min": 0.19667086005210876, "max": 3.9180712699890137, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 269.01801801801804, "min": 242.60162601626016, "max": 992.516129032258, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29861.0, "min": 17450.0, "max": 32821.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7129603390758101, "min": -0.928929082808956, "max": 1.757398356388255, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 190.13859763741493, "min": -28.796801567077637, "max": 216.15999783575535, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7129603390758101, "min": -0.928929082808956, "max": 1.757398356388255, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 190.13859763741493, "min": -28.796801567077637, "max": 216.15999783575535, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03898474175851637, "min": 0.03579492737054995, "max": 9.307819741260674, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.327306335195317, "min": 4.327306335195317, "max": 167.54075534269214, "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": "1734224061", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1734227796" }, "total": 3734.4861459480003, "count": 1, "self": 0.7442452810005307, "children": { "run_training.setup": { "total": 0.08567339599994739, "count": 1, "self": 0.08567339599994739 }, "TrainerController.start_learning": { "total": 3733.656227271, "count": 1, "self": 2.3258756500417803, "children": { "TrainerController._reset_env": { "total": 7.149475273000007, "count": 1, "self": 7.149475273000007 }, "TrainerController.advance": { "total": 3724.0844160139573, "count": 64287, "self": 2.4799703210978805, "children": { "env_step": { "total": 2572.8057086688705, "count": 64287, "self": 2407.55905183686, "children": { "SubprocessEnvManager._take_step": { "total": 163.74231810997117, "count": 64287, "self": 6.985091713972679, "children": { "TorchPolicy.evaluate": { "total": 156.7572263959985, "count": 62554, "self": 156.7572263959985 } } }, "workers": { "total": 1.5043387220396198, "count": 64287, "self": 0.0, "children": { "worker_root": { "total": 3726.181707121919, "count": 64287, "is_parallel": true, "self": 1505.5052545249223, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0036498389999906067, "count": 1, "is_parallel": true, "self": 0.0012262340000006589, "children": { "_process_rank_one_or_two_observation": { "total": 0.002423604999989948, "count": 8, "is_parallel": true, "self": 0.002423604999989948 } } }, "UnityEnvironment.step": { "total": 0.06984606499997881, "count": 1, "is_parallel": true, "self": 0.000907689999962713, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000636894999956894, "count": 1, "is_parallel": true, "self": 0.000636894999956894 }, "communicator.exchange": { "total": 0.06602473700002065, "count": 1, "is_parallel": true, "self": 0.06602473700002065 }, "steps_from_proto": { "total": 0.0022767430000385502, "count": 1, "is_parallel": true, "self": 0.0004938820000006672, "children": { "_process_rank_one_or_two_observation": { "total": 0.001782861000037883, "count": 8, "is_parallel": true, "self": 0.001782861000037883 } } } } } } }, "UnityEnvironment.step": { "total": 2220.6764525969966, "count": 64286, "is_parallel": true, "self": 57.17260016098953, "children": { "UnityEnvironment._generate_step_input": { "total": 34.92766388501718, "count": 64286, "is_parallel": true, "self": 34.92766388501718 }, "communicator.exchange": { "total": 1983.0383064869516, "count": 64286, "is_parallel": true, "self": 1983.0383064869516 }, "steps_from_proto": { "total": 145.53788206403817, "count": 64286, "is_parallel": true, "self": 30.411831057882637, "children": { "_process_rank_one_or_two_observation": { "total": 115.12605100615554, "count": 514288, "is_parallel": true, "self": 115.12605100615554 } } } } } } } } } } }, "trainer_advance": { "total": 1148.7987370239891, "count": 64287, "self": 4.068511527960027, "children": { "process_trajectory": { "total": 175.85607037002603, "count": 64287, "self": 175.52063816502562, "children": { "RLTrainer._checkpoint": { "total": 0.3354322050004157, "count": 2, "self": 0.3354322050004157 } } }, "_update_policy": { "total": 968.874155126003, "count": 459, "self": 402.23629688097026, "children": { "TorchPPOOptimizer.update": { "total": 566.6378582450327, "count": 22806, "self": 566.6378582450327 } } } } } } }, "trainer_threads": { "total": 2.016000507865101e-06, "count": 1, "self": 2.016000507865101e-06 }, "TrainerController._save_models": { "total": 0.09645831800025917, "count": 1, "self": 0.002015907999521005, "children": { "RLTrainer._checkpoint": { "total": 0.09444241000073816, "count": 1, "self": 0.09444241000073816 } } } } } } }