{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2017671912908554, "min": 0.1956200748682022, "max": 0.3468891680240631, "count": 17 }, "Pyramids.Policy.Entropy.sum": { "value": 6001.36328125, "min": 5887.3818359375, "max": 10467.7275390625, "count": 17 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 238.6315789473684, "min": 232.609375, "max": 322.23333333333335, "count": 17 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27204.0, "min": 18453.0, "max": 32423.0, "count": 17 }, "Pyramids.Step.mean": { "value": 1499984.0, "min": 1019951.0, "max": 1499984.0, "count": 17 }, "Pyramids.Step.sum": { "value": 1499984.0, "min": 1019951.0, "max": 1499984.0, "count": 17 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7601009607315063, "min": 0.6408032178878784, "max": 0.7900497913360596, "count": 17 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 126.93685913085938, "min": 79.10871887207031, "max": 138.2587127685547, "count": 17 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.017158646136522293, "min": 0.014697253704071045, "max": 0.019293153658509254, "count": 17 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.8654937744140625, "min": 2.180126428604126, "max": 3.207824230194092, "count": 17 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.747333312243746, "min": 1.5924821979469723, "max": 1.7672868003678877, "count": 17 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 199.19599759578705, "min": 121.72819799184799, "max": 227.9799972474575, "count": 17 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.747333312243746, "min": 1.5924821979469723, "max": 1.7672868003678877, "count": 17 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 199.19599759578705, "min": 121.72819799184799, "max": 227.9799972474575, "count": 17 }, "Pyramids.Policy.RndReward.mean": { "value": 0.035691248115510554, "min": 0.035691248115510554, "max": 0.05215429211080925, "count": 17 }, "Pyramids.Policy.RndReward.sum": { "value": 4.0688022851682035, "min": 3.314780578162754, "max": 5.48682291759178, "count": 17 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06969928937371957, "min": 0.06422369384687167, "max": 0.07258907158189605, "count": 17 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.975790051232074, "min": 0.5649106561759034, "max": 1.0162470021465446, "count": 17 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015370686575162213, "min": 0.012745629658228627, "max": 0.016346135751743075, "count": 17 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21518961205227097, "min": 0.11912501468425013, "max": 0.22884590052440307, "count": 17 }, "Pyramids.Policy.LearningRate.mean": { "value": 4.928670442857142e-06, "min": 4.928670442857142e-06, "max": 0.0001629690257395417, "count": 17 }, "Pyramids.Policy.LearningRate.sum": { "value": 6.90013862e-05, "min": 6.90013862e-05, "max": 0.0021713462990642666, "count": 17 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10098571428571432, "min": 0.10098571428571432, "max": 0.13259379166666665, "count": 17 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4138000000000004, "min": 1.0607503333333332, "max": 1.8342690666666668, "count": 17 }, "Pyramids.Policy.Beta.mean": { "value": 0.00010847285714285718, "min": 0.00010847285714285718, "max": 0.0032661197875, "count": 17 }, "Pyramids.Policy.Beta.sum": { "value": 0.0015186200000000005, "min": 0.0015186200000000005, "max": 0.043523479760000004, "count": 17 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01440468244254589, "min": 0.01424525398761034, "max": 0.01760612055659294, "count": 17 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20166555047035217, "min": 0.13917449116706848, "max": 0.24648568034172058, "count": 17 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 17 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 17 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1731687124", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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 --resume --no-graphics --torch-device cuda:0 --no-graphics --debug", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1731688410" }, "total": 1286.1273987120003, "count": 1, "self": 0.48131996800111665, "children": { "run_training.setup": { "total": 0.07746751900049276, "count": 1, "self": 0.07746751900049276 }, "TrainerController.start_learning": { "total": 1285.5686112249987, "count": 1, "self": 0.6796937353956309, "children": { "TrainerController._reset_env": { "total": 2.9247552739998355, "count": 1, "self": 2.9247552739998355 }, "TrainerController.advance": { "total": 1281.8517803436025, "count": 32811, "self": 0.7368759017263073, "children": { "env_step": { "total": 924.4362790809355, "count": 32811, "self": 838.0878667697652, "children": { "SubprocessEnvManager._take_step": { "total": 85.93083537592793, "count": 32811, "self": 2.341578512063279, "children": { "TorchPolicy.evaluate": { "total": 83.58925686386465, "count": 31340, "self": 83.58925686386465 } } }, "workers": { "total": 0.4175769352423231, "count": 32811, "self": 0.0, "children": { "worker_root": { "total": 1282.916554070889, "count": 32811, "is_parallel": true, "self": 503.96048706200054, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002794324000205961, "count": 1, "is_parallel": true, "self": 0.0007855459953134414, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020087780048925197, "count": 8, "is_parallel": true, "self": 0.0020087780048925197 } } }, "UnityEnvironment.step": { "total": 0.059342993999962346, "count": 1, "is_parallel": true, "self": 0.0006536159999086522, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004605960002663778, "count": 1, "is_parallel": true, "self": 0.0004605960002663778 }, "communicator.exchange": { "total": 0.05661947800035705, "count": 1, "is_parallel": true, "self": 0.05661947800035705 }, "steps_from_proto": { "total": 0.0016093039994302671, "count": 1, "is_parallel": true, "self": 0.0003353039992362028, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012740000001940643, "count": 8, "is_parallel": true, "self": 0.0012740000001940643 } } } } } } }, "UnityEnvironment.step": { "total": 778.9560670088886, "count": 32810, "is_parallel": true, "self": 16.734177104233822, "children": { "UnityEnvironment._generate_step_input": { "total": 11.052866471871312, "count": 32810, "is_parallel": true, "self": 11.052866471871312 }, "communicator.exchange": { "total": 702.7962260299992, "count": 32810, "is_parallel": true, "self": 702.7962260299992 }, "steps_from_proto": { "total": 48.37279740278427, "count": 32810, "is_parallel": true, "self": 9.710107740927924, "children": { "_process_rank_one_or_two_observation": { "total": 38.66268966185635, "count": 262480, "is_parallel": true, "self": 38.66268966185635 } } } } } } } } } } }, "trainer_advance": { "total": 356.6786253609407, "count": 32811, "self": 1.5444829939115152, "children": { "process_trajectory": { "total": 70.74342205103676, "count": 32811, "self": 70.58841375103657, "children": { "RLTrainer._checkpoint": { "total": 0.1550083000001905, "count": 1, "self": 0.1550083000001905 } } }, "_update_policy": { "total": 284.39072031599244, "count": 231, "self": 154.880350986974, "children": { "TorchPPOOptimizer.update": { "total": 129.51036932901843, "count": 11382, "self": 129.51036932901843 } } } } } } }, "trainer_threads": { "total": 7.970011211000383e-07, "count": 1, "self": 7.970011211000383e-07 }, "TrainerController._save_models": { "total": 0.1123810749995755, "count": 1, "self": 0.0019194329997844761, "children": { "RLTrainer._checkpoint": { "total": 0.11046164199979103, "count": 1, "self": 0.11046164199979103 } } } } } } }