{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.17980921268463135, "min": 0.17980921268463135, "max": 1.4908032417297363, "count": 68 }, "Pyramids.Policy.Entropy.sum": { "value": 5397.1533203125, "min": 5397.1533203125, "max": 45225.0078125, "count": 68 }, "Pyramids.Step.mean": { "value": 2039938.0, "min": 29952.0, "max": 2039938.0, "count": 68 }, "Pyramids.Step.sum": { "value": 2039938.0, "min": 29952.0, "max": 2039938.0, "count": 68 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8179959654808044, "min": -0.10204073786735535, "max": 0.8437695503234863, "count": 68 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 247.0347900390625, "min": -24.489776611328125, "max": 253.2827911376953, "count": 68 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.008990243077278137, "min": -0.005866355262696743, "max": 0.23719657957553864, "count": 68 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.7150533199310303, "min": -1.7833720445632935, "max": 56.92717742919922, "count": 68 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06704078006270506, "min": 0.0645019569540532, "max": 0.07243784507621616, "count": 68 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9385709208778708, "min": 0.49196040106939964, "max": 1.073367096163565, "count": 68 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01307627064134653, "min": 0.00015572338776235944, "max": 0.017449374461735022, "count": 68 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18306778897885143, "min": 0.0017129572653859539, "max": 0.2442912424642903, "count": 68 }, "Pyramids.Policy.LearningRate.mean": { "value": 9.748766750413332e-05, "min": 9.748766750413332e-05, "max": 0.00029838354339596195, "count": 68 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0013648273450578665, "min": 0.0013648273450578665, "max": 0.0037595075468308662, "count": 68 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.13249586666666666, "min": 0.13249586666666666, "max": 0.19946118095238097, "count": 68 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.8549421333333331, "min": 1.3962282666666668, "max": 2.737527966666667, "count": 68 }, "Pyramids.Policy.Beta.mean": { "value": 0.0032563370800000003, "min": 0.0032563370800000003, "max": 0.009946171977142856, "count": 68 }, "Pyramids.Policy.Beta.sum": { "value": 0.04558871912, "min": 0.04558871912, "max": 0.12533159642, "count": 68 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007266219239681959, "min": 0.00682816794142127, "max": 0.38205215334892273, "count": 68 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10172706842422485, "min": 0.09559435397386551, "max": 2.6743650436401367, "count": 68 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 244.416, "min": 217.78195488721803, "max": 999.0, "count": 68 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30552.0, "min": 15984.0, "max": 32746.0, "count": 68 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7395823949575424, "min": -1.0000000521540642, "max": 1.7822180306328868, "count": 68 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 217.4477993696928, "min": -31.999601677060127, "max": 237.03499807417393, "count": 68 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7395823949575424, "min": -1.0000000521540642, "max": 1.7822180306328868, "count": 68 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 217.4477993696928, "min": -31.999601677060127, "max": 237.03499807417393, "count": 68 }, "Pyramids.Policy.RndReward.mean": { "value": 0.018703219723756773, "min": 0.015945801764260102, "max": 7.945512444712222, "count": 68 }, "Pyramids.Policy.RndReward.sum": { "value": 2.337902465469597, "min": 2.07823581318371, "max": 127.12819911539555, "count": 68 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 68 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 68 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1736590425", "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": "1736595685" }, "total": 5259.843416490001, "count": 1, "self": 0.3866337450008359, "children": { "run_training.setup": { "total": 0.05692282600011822, "count": 1, "self": 0.05692282600011822 }, "TrainerController.start_learning": { "total": 5259.399859919, "count": 1, "self": 3.2217839600052685, "children": { "TrainerController._reset_env": { "total": 2.18508397100004, "count": 1, "self": 2.18508397100004 }, "TrainerController.advance": { "total": 5253.857490259995, "count": 133187, "self": 3.3552704809671923, "children": { "env_step": { "total": 3793.8598952431466, "count": 133187, "self": 3462.0814241241583, "children": { "SubprocessEnvManager._take_step": { "total": 329.9098882581161, "count": 133187, "self": 10.118870759019046, "children": { "TorchPolicy.evaluate": { "total": 319.79101749909705, "count": 128800, "self": 319.79101749909705 } } }, "workers": { "total": 1.8685828608722659, "count": 133186, "self": 0.0, "children": { "worker_root": { "total": 5248.689558098246, "count": 133186, "is_parallel": true, "self": 2045.0334780562785, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021429349999380065, "count": 1, "is_parallel": true, "self": 0.00070007899967095, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014428560002670565, "count": 8, "is_parallel": true, "self": 0.0014428560002670565 } } }, "UnityEnvironment.step": { "total": 0.05158772899994801, "count": 1, "is_parallel": true, "self": 0.0006383649997587781, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005218189999141032, "count": 1, "is_parallel": true, "self": 0.0005218189999141032 }, "communicator.exchange": { "total": 0.0486770739998974, "count": 1, "is_parallel": true, "self": 0.0486770739998974 }, "steps_from_proto": { "total": 0.001750471000377729, "count": 1, "is_parallel": true, "self": 0.00037436999946294236, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013761010009147867, "count": 8, "is_parallel": true, "self": 0.0013761010009147867 } } } } } } }, "UnityEnvironment.step": { "total": 3203.656080041968, "count": 133185, "is_parallel": true, "self": 71.36936587535683, "children": { "UnityEnvironment._generate_step_input": { "total": 49.997467591988425, "count": 133185, "is_parallel": true, "self": 49.997467591988425 }, "communicator.exchange": { "total": 2865.762534146872, "count": 133185, "is_parallel": true, "self": 2865.762534146872 }, "steps_from_proto": { "total": 216.52671242775068, "count": 133185, "is_parallel": true, "self": 45.29428247979649, "children": { "_process_rank_one_or_two_observation": { "total": 171.2324299479542, "count": 1065480, "is_parallel": true, "self": 171.2324299479542 } } } } } } } } } } }, "trainer_advance": { "total": 1456.6423245358815, "count": 133186, "self": 5.897573797948098, "children": { "process_trajectory": { "total": 293.17314737793413, "count": 133186, "self": 292.7749743799336, "children": { "RLTrainer._checkpoint": { "total": 0.3981729980005184, "count": 4, "self": 0.3981729980005184 } } }, "_update_policy": { "total": 1157.5716033599992, "count": 942, "self": 650.7413175971578, "children": { "TorchPPOOptimizer.update": { "total": 506.8302857628414, "count": 46998, "self": 506.8302857628414 } } } } } } }, "trainer_threads": { "total": 1.5240002539940178e-06, "count": 1, "self": 1.5240002539940178e-06 }, "TrainerController._save_models": { "total": 0.13550020399998175, "count": 1, "self": 0.002136614999471931, "children": { "RLTrainer._checkpoint": { "total": 0.13336358900050982, "count": 1, "self": 0.13336358900050982 } } } } } } }