{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.17392335832118988, "min": 0.16836991906166077, "max": 1.413450837135315, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5237.18017578125, "min": 5034.93408203125, "max": 42878.4453125, "count": 100 }, "Pyramids.Step.mean": { "value": 2999882.0, "min": 29952.0, "max": 2999882.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999882.0, "min": 29952.0, "max": 2999882.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6882781386375427, "min": -0.11751057952642441, "max": 0.7866436243057251, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 201.66549682617188, "min": -28.202539443969727, "max": 234.57614135742188, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.010027213953435421, "min": -0.01762033812701702, "max": 0.36040055751800537, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.937973737716675, "min": -4.775111675262451, "max": 85.41493225097656, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06933751382166518, "min": 0.06449492732999425, "max": 0.0735905387289483, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9707251935033127, "min": 0.4697863167732547, "max": 1.1020367980196242, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015186713332825874, "min": 0.00016508900351663104, "max": 0.017606275055662816, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21261398665956224, "min": 0.0023112460492328347, "max": 0.24648785077927943, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.550292340411904e-06, "min": 1.550292340411904e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.1704092765766657e-05, "min": 2.1704092765766657e-05, "max": 0.0038856619047793993, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10051673095238098, "min": 0.10051673095238098, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4072342333333336, "min": 1.3897045333333333, "max": 2.7226403000000006, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.162142214285713e-05, "min": 6.162142214285713e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008626999099999997, "min": 0.0008626999099999997, "max": 0.12953253794, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.003167995484545827, "min": 0.003140446962788701, "max": 0.3246123194694519, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.044351935386657715, "min": 0.04396625608205795, "max": 2.2722861766815186, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 259.45299145299145, "min": 238.376, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30356.0, "min": 15984.0, "max": 33359.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.67214528299295, "min": -1.0000000521540642, "max": 1.7622096632276811, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 195.64099811017513, "min": -32.000001668930054, "max": 223.72759833931923, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.67214528299295, "min": -1.0000000521540642, "max": 1.7622096632276811, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 195.64099811017513, "min": -32.000001668930054, "max": 223.72759833931923, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.008575285745970706, "min": 0.008048553094105897, "max": 6.2704182378947735, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.0033084322785726, "min": 0.9322681011180975, "max": 100.32669180631638, "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": "1742038813", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1742045904" }, "total": 7091.216942025, "count": 1, "self": 0.5410416890008491, "children": { "run_training.setup": { "total": 0.02532093199999963, "count": 1, "self": 0.02532093199999963 }, "TrainerController.start_learning": { "total": 7090.6505794039995, "count": 1, "self": 4.3786091758856855, "children": { "TrainerController._reset_env": { "total": 3.1122940539999036, "count": 1, "self": 3.1122940539999036 }, "TrainerController.advance": { "total": 7083.069954167114, "count": 193689, "self": 4.34915699008252, "children": { "env_step": { "total": 5041.324324810014, "count": 193689, "self": 4574.320752751824, "children": { "SubprocessEnvManager._take_step": { "total": 464.5638967561756, "count": 193689, "self": 14.259012773027848, "children": { "TorchPolicy.evaluate": { "total": 450.30488398314776, "count": 187559, "self": 450.30488398314776 } } }, "workers": { "total": 2.4396753020142796, "count": 193689, "self": 0.0, "children": { "worker_root": { "total": 7075.358391417929, "count": 193689, "is_parallel": true, "self": 2848.8308745297118, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005698793000078695, "count": 1, "is_parallel": true, "self": 0.0036743550003848213, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020244379996938733, "count": 8, "is_parallel": true, "self": 0.0020244379996938733 } } }, "UnityEnvironment.step": { "total": 0.04859230500005651, "count": 1, "is_parallel": true, "self": 0.0005317780000950734, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045386099998268037, "count": 1, "is_parallel": true, "self": 0.00045386099998268037 }, "communicator.exchange": { "total": 0.045902371000011044, "count": 1, "is_parallel": true, "self": 0.045902371000011044 }, "steps_from_proto": { "total": 0.0017042949999677148, "count": 1, "is_parallel": true, "self": 0.0004884229999788658, "children": { "_process_rank_one_or_two_observation": { "total": 0.001215871999988849, "count": 8, "is_parallel": true, "self": 0.001215871999988849 } } } } } } }, "UnityEnvironment.step": { "total": 4226.527516888217, "count": 193688, "is_parallel": true, "self": 97.372906348387, "children": { "UnityEnvironment._generate_step_input": { "total": 69.46087891490095, "count": 193688, "is_parallel": true, "self": 69.46087891490095 }, "communicator.exchange": { "total": 3765.91910061198, "count": 193688, "is_parallel": true, "self": 3765.91910061198 }, "steps_from_proto": { "total": 293.7746310129496, "count": 193688, "is_parallel": true, "self": 60.58179606488409, "children": { "_process_rank_one_or_two_observation": { "total": 233.19283494806552, "count": 1549504, "is_parallel": true, "self": 233.19283494806552 } } } } } } } } } } }, "trainer_advance": { "total": 2037.3964723670174, "count": 193689, "self": 8.54307107712134, "children": { "process_trajectory": { "total": 392.96548294191416, "count": 193689, "self": 392.3240244729136, "children": { "RLTrainer._checkpoint": { "total": 0.641458469000554, "count": 6, "self": 0.641458469000554 } } }, "_update_policy": { "total": 1635.887918347982, "count": 1388, "self": 896.8204156231088, "children": { "TorchPPOOptimizer.update": { "total": 739.0675027248731, "count": 68409, "self": 739.0675027248731 } } } } } } }, "trainer_threads": { "total": 9.039995347848162e-07, "count": 1, "self": 9.039995347848162e-07 }, "TrainerController._save_models": { "total": 0.08972110300055647, "count": 1, "self": 0.0016737750001993845, "children": { "RLTrainer._checkpoint": { "total": 0.08804732800035708, "count": 1, "self": 0.08804732800035708 } } } } } } }