{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6080633997917175, "min": 0.5794950723648071, "max": 1.3749773502349854, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18261.359375, "min": 17403.396484375, "max": 41711.3125, "count": 33 }, "Pyramids.Step.mean": { "value": 989973.0, "min": 29981.0, "max": 989973.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989973.0, "min": 29981.0, "max": 989973.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5271888971328735, "min": -0.0967899039387703, "max": 0.5271888971328735, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 142.34100341796875, "min": -23.326366424560547, "max": 142.34100341796875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03477299585938454, "min": 0.0020750879775732756, "max": 0.39330095052719116, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.38870906829834, "min": 0.5664989948272705, "max": 93.95552062988281, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06833529743375401, "min": 0.06421989302239114, "max": 0.07439208805242031, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.956694164072556, "min": 0.5067249919065734, "max": 1.0788671257323585, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013019752658440383, "min": 9.594691497062908e-05, "max": 0.013210731247382845, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18227653721816536, "min": 0.001151362979647549, "max": 0.18227653721816536, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.688883151357148e-06, "min": 7.688883151357148e-06, "max": 0.0002952371587304714, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010764436411900006, "min": 0.00010764436411900006, "max": 0.0033316527894490995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256292857142858, "min": 0.10256292857142858, "max": 0.1984123857142857, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358810000000002, "min": 1.3888867, "max": 2.3590103, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026603656428571444, "min": 0.00026603656428571444, "max": 0.009841397332857143, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037245119000000023, "min": 0.0037245119000000023, "max": 0.11106403491000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00990848708897829, "min": 0.00990848708897829, "max": 0.5971961617469788, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13871881365776062, "min": 0.13871881365776062, "max": 4.180373191833496, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 382.8181818181818, "min": 382.8181818181818, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29477.0, "min": 16652.0, "max": 33536.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5418640837455406, "min": -0.9999500517733395, "max": 1.5418640837455406, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 120.26539853215218, "min": -31.998401656746864, "max": 120.26539853215218, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5418640837455406, "min": -0.9999500517733395, "max": 1.5418640837455406, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 120.26539853215218, "min": -31.998401656746864, "max": 120.26539853215218, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03879514770456948, "min": 0.03879514770456948, "max": 11.882982588866177, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0260215209564194, "min": 3.0260215209564194, "max": 202.01070401072502, "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": "1775497757", "python_version": "3.10.12 (main, Mar 3 2026, 11:56:32) [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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1775500050" }, "total": 2293.0654471510006, "count": 1, "self": 0.7802521339999657, "children": { "run_training.setup": { "total": 0.021837672000401653, "count": 1, "self": 0.021837672000401653 }, "TrainerController.start_learning": { "total": 2292.2633573450003, "count": 1, "self": 1.6101357810475747, "children": { "TrainerController._reset_env": { "total": 2.1668558359997405, "count": 1, "self": 2.1668558359997405 }, "TrainerController.advance": { "total": 2288.408423199953, "count": 63564, "self": 1.650957412050957, "children": { "env_step": { "total": 1598.2374452760068, "count": 63564, "self": 1435.0295568751908, "children": { "SubprocessEnvManager._take_step": { "total": 162.28292497788607, "count": 63564, "self": 5.043274802073029, "children": { "TorchPolicy.evaluate": { "total": 157.23965017581304, "count": 62575, "self": 157.23965017581304 } } }, "workers": { "total": 0.9249634229299772, "count": 63564, "self": 0.0, "children": { "worker_root": { "total": 2285.914404635807, "count": 63564, "is_parallel": true, "self": 976.4977078129332, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001891985999463941, "count": 1, "is_parallel": true, "self": 0.0006545079995703418, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012374779998935992, "count": 8, "is_parallel": true, "self": 0.0012374779998935992 } } }, "UnityEnvironment.step": { "total": 0.053762614000334, "count": 1, "is_parallel": true, "self": 0.000595501999669068, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005065980003564619, "count": 1, "is_parallel": true, "self": 0.0005065980003564619 }, "communicator.exchange": { "total": 0.05084130399973219, "count": 1, "is_parallel": true, "self": 0.05084130399973219 }, "steps_from_proto": { "total": 0.0018192100005762768, "count": 1, "is_parallel": true, "self": 0.00041600600252422737, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014032039980520494, "count": 8, "is_parallel": true, "self": 0.0014032039980520494 } } } } } } }, "UnityEnvironment.step": { "total": 1309.4166968228737, "count": 63563, "is_parallel": true, "self": 35.55065125681085, "children": { "UnityEnvironment._generate_step_input": { "total": 25.18237793308799, "count": 63563, "is_parallel": true, "self": 25.18237793308799 }, "communicator.exchange": { "total": 1129.8040881090246, "count": 63563, "is_parallel": true, "self": 1129.8040881090246 }, "steps_from_proto": { "total": 118.87957952395027, "count": 63563, "is_parallel": true, "self": 24.95178377085631, "children": { "_process_rank_one_or_two_observation": { "total": 93.92779575309396, "count": 508504, "is_parallel": true, "self": 93.92779575309396 } } } } } } } } } } }, "trainer_advance": { "total": 688.5200205118954, "count": 63564, "self": 2.7500540260080015, "children": { "process_trajectory": { "total": 132.56792192287776, "count": 63564, "self": 132.37545110787778, "children": { "RLTrainer._checkpoint": { "total": 0.19247081499997876, "count": 2, "self": 0.19247081499997876 } } }, "_update_policy": { "total": 553.2020445630096, "count": 441, "self": 306.96609290804554, "children": { "TorchPPOOptimizer.update": { "total": 246.23595165496408, "count": 22839, "self": 246.23595165496408 } } } } } } }, "trainer_threads": { "total": 9.309997039963491e-07, "count": 1, "self": 9.309997039963491e-07 }, "TrainerController._save_models": { "total": 0.07794159700006276, "count": 1, "self": 0.0010060080003313487, "children": { "RLTrainer._checkpoint": { "total": 0.07693558899973141, "count": 1, "self": 0.07693558899973141 } } } } } } }