{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1407463252544403, "min": 0.1407463252544403, "max": 1.4516788721084595, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4231.3974609375, "min": 4225.279296875, "max": 44038.12890625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999965.0, "min": 29952.0, "max": 2999965.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999965.0, "min": 29952.0, "max": 2999965.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8429033160209656, "min": -0.10632847249507904, "max": 0.9037237763404846, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 252.87100219726562, "min": -25.51883316040039, "max": 281.99542236328125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.04178939014673233, "min": -0.10877136886119843, "max": 0.3733639717102051, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -12.536816596984863, "min": -30.129669189453125, "max": 90.35408020019531, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06950191439578443, "min": 0.06422240086037115, "max": 0.07369302799564872, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.973026801540982, "min": 0.49739308440361985, "max": 1.0703216729390062, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013833994909348777, "min": 0.0006428850874306308, "max": 0.017201594533010695, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19367592873088288, "min": 0.00771462104916757, "max": 0.25802391799516045, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4265423816619017e-06, "min": 1.4265423816619017e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 1.9971593343266625e-05, "min": 1.9971593343266625e-05, "max": 0.0040278844573719, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10047548095238097, "min": 0.10047548095238097, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4066567333333335, "min": 1.3962282666666668, "max": 2.8426281, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.7500547142857044e-05, "min": 5.7500547142857044e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008050076599999986, "min": 0.0008050076599999986, "max": 0.13427854719, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005957638379186392, "min": 0.005547248292714357, "max": 0.4484875500202179, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08340694010257721, "min": 0.07766147702932358, "max": 3.1394128799438477, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 212.42028985507247, "min": 199.60416666666666, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29314.0, "min": 15984.0, "max": 32619.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.770940995688061, "min": -1.0000000521540642, "max": 1.801227572149244, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 246.1607984006405, "min": -29.873001642525196, "max": 265.8399978876114, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.770940995688061, "min": -1.0000000521540642, "max": 1.801227572149244, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 246.1607984006405, "min": -29.873001642525196, "max": 265.8399978876114, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.01317794127419102, "min": 0.012155146355723479, "max": 8.604273051954806, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.8317338371125516, "min": 1.6409447580226697, "max": 137.6683688312769, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1687860586", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "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": "1687868839" }, "total": 8253.275844823, "count": 1, "self": 0.5246846749996621, "children": { "run_training.setup": { "total": 0.04155062000063481, "count": 1, "self": 0.04155062000063481 }, "TrainerController.start_learning": { "total": 8252.709609528, "count": 1, "self": 5.113557733819107, "children": { "TrainerController._reset_env": { "total": 5.193380597000214, "count": 1, "self": 5.193380597000214 }, "TrainerController.advance": { "total": 8242.302402935178, "count": 195723, "self": 5.019888898857971, "children": { "env_step": { "total": 6193.7764083752945, "count": 195723, "self": 5813.541124236284, "children": { "SubprocessEnvManager._take_step": { "total": 377.3174736578494, "count": 195723, "self": 16.54147532087245, "children": { "TorchPolicy.evaluate": { "total": 360.77599833697695, "count": 187552, "self": 360.77599833697695 } } }, "workers": { "total": 2.9178104811608137, "count": 195723, "self": 0.0, "children": { "worker_root": { "total": 8233.256749788878, "count": 195723, "is_parallel": true, "self": 2818.7819589965893, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020864379994236515, "count": 1, "is_parallel": true, "self": 0.000695000001542212, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013914379978814395, "count": 8, "is_parallel": true, "self": 0.0013914379978814395 } } }, "UnityEnvironment.step": { "total": 0.11274867700012692, "count": 1, "is_parallel": true, "self": 0.0005877670000700164, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005948520001766155, "count": 1, "is_parallel": true, "self": 0.0005948520001766155 }, "communicator.exchange": { "total": 0.10955815099987376, "count": 1, "is_parallel": true, "self": 0.10955815099987376 }, "steps_from_proto": { "total": 0.0020079070000065258, "count": 1, "is_parallel": true, "self": 0.0003795319971686695, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016283750028378563, "count": 8, "is_parallel": true, "self": 0.0016283750028378563 } } } } } } }, "UnityEnvironment.step": { "total": 5414.474790792288, "count": 195722, "is_parallel": true, "self": 108.89185503772478, "children": { "UnityEnvironment._generate_step_input": { "total": 78.36613787992701, "count": 195722, "is_parallel": true, "self": 78.36613787992701 }, "communicator.exchange": { "total": 4867.362272635879, "count": 195722, "is_parallel": true, "self": 4867.362272635879 }, "steps_from_proto": { "total": 359.85452523875756, "count": 195722, "is_parallel": true, "self": 73.60721413430383, "children": { "_process_rank_one_or_two_observation": { "total": 286.24731110445373, "count": 1565776, "is_parallel": true, "self": 286.24731110445373 } } } } } } } } } } }, "trainer_advance": { "total": 2043.5061056610257, "count": 195723, "self": 9.67736405537562, "children": { "process_trajectory": { "total": 380.27020750860174, "count": 195723, "self": 379.5756974886008, "children": { "RLTrainer._checkpoint": { "total": 0.694510020000962, "count": 6, "self": 0.694510020000962 } } }, "_update_policy": { "total": 1653.5585340970483, "count": 1398, "self": 1055.1552172450565, "children": { "TorchPPOOptimizer.update": { "total": 598.4033168519918, "count": 68376, "self": 598.4033168519918 } } } } } } }, "trainer_threads": { "total": 1.170001269201748e-06, "count": 1, "self": 1.170001269201748e-06 }, "TrainerController._save_models": { "total": 0.10026709200064943, "count": 1, "self": 0.001480752000134089, "children": { "RLTrainer._checkpoint": { "total": 0.09878634000051534, "count": 1, "self": 0.09878634000051534 } } } } } } }