{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7005102634429932, "min": 0.7005102634429932, "max": 1.4899113178253174, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 20914.43359375, "min": 20914.43359375, "max": 45197.94921875, "count": 33 }, "Pyramids.Step.mean": { "value": 989889.0, "min": 29890.0, "max": 989889.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989889.0, "min": 29890.0, "max": 989889.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3922243118286133, "min": -0.178433358669281, "max": 0.4292246401309967, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 104.3316650390625, "min": -42.467140197753906, "max": 114.17375183105469, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.025996580719947815, "min": -0.03232503682374954, "max": 0.26009249687194824, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -6.915090560913086, "min": -8.275209426879883, "max": 61.902015686035156, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07249576760417162, "min": 0.0639663716316411, "max": 0.07452998307384538, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0149407464584026, "min": 0.5799586704494593, "max": 1.055467549809049, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014416007904093078, "min": 7.864274907139885e-05, "max": 0.014416007904093078, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2018241106573031, "min": 0.0011009984869995838, "max": 0.2018241106573031, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.259261865992856e-06, "min": 7.259261865992856e-06, "max": 0.0002947698392433875, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010162966612389998, "min": 0.00010162966612389998, "max": 0.0033835835721389004, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024197214285714, "min": 0.1024197214285714, "max": 0.19825661249999998, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4338760999999998, "min": 1.4338760999999998, "max": 2.5278611, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002517301707142858, "min": 0.0002517301707142858, "max": 0.009825835588750002, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035242223900000006, "min": 0.0035242223900000006, "max": 0.11281332389000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008060975931584835, "min": 0.008060975931584835, "max": 0.3066112995147705, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11285366863012314, "min": 0.11285366863012314, "max": 2.452890396118164, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 442.01428571428573, "min": 422.8787878787879, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30941.0, "min": 17328.0, "max": 32931.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4390666437321815, "min": -0.9999419873760592, "max": 1.4531044502978894, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 99.29559841752052, "min": -30.998201608657837, "max": 99.29559841752052, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4390666437321815, "min": -0.9999419873760592, "max": 1.4531044502978894, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 99.29559841752052, "min": -30.998201608657837, "max": 99.29559841752052, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03815904078399636, "min": 0.03643144154790858, "max": 6.362992232354979, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.632973814095749, "min": 2.440906583709875, "max": 114.53386018238962, "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": "1752070726", "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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1752072826" }, "total": 2100.336689523, "count": 1, "self": 0.47594196600084615, "children": { "run_training.setup": { "total": 0.01938771099958103, "count": 1, "self": 0.01938771099958103 }, "TrainerController.start_learning": { "total": 2099.8413598459997, "count": 1, "self": 1.1863590560283228, "children": { "TrainerController._reset_env": { "total": 2.1372539079998205, "count": 1, "self": 2.1372539079998205 }, "TrainerController.advance": { "total": 2096.436267752972, "count": 63488, "self": 1.320345641993299, "children": { "env_step": { "total": 1457.8372393780573, "count": 63488, "self": 1315.0992466970974, "children": { "SubprocessEnvManager._take_step": { "total": 142.0120474718551, "count": 63488, "self": 4.3782055877995845, "children": { "TorchPolicy.evaluate": { "total": 137.63384188405553, "count": 62553, "self": 137.63384188405553 } } }, "workers": { "total": 0.7259452091047933, "count": 63488, "self": 0.0, "children": { "worker_root": { "total": 2094.975901201101, "count": 63488, "is_parallel": true, "self": 887.5006538440944, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017048559998329438, "count": 1, "is_parallel": true, "self": 0.000562718998935452, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011421370008974918, "count": 8, "is_parallel": true, "self": 0.0011421370008974918 } } }, "UnityEnvironment.step": { "total": 0.05692181500035076, "count": 1, "is_parallel": true, "self": 0.000541477000751911, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004398149999360612, "count": 1, "is_parallel": true, "self": 0.0004398149999360612 }, "communicator.exchange": { "total": 0.054387365999900794, "count": 1, "is_parallel": true, "self": 0.054387365999900794 }, "steps_from_proto": { "total": 0.0015531569997619954, "count": 1, "is_parallel": true, "self": 0.00033723999968060525, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012159170000813901, "count": 8, "is_parallel": true, "self": 0.0012159170000813901 } } } } } } }, "UnityEnvironment.step": { "total": 1207.4752473570065, "count": 63487, "is_parallel": true, "self": 31.117190372985988, "children": { "UnityEnvironment._generate_step_input": { "total": 22.34756389995073, "count": 63487, "is_parallel": true, "self": 22.34756389995073 }, "communicator.exchange": { "total": 1060.7410423419697, "count": 63487, "is_parallel": true, "self": 1060.7410423419697 }, "steps_from_proto": { "total": 93.26945074210016, "count": 63487, "is_parallel": true, "self": 18.68292743207303, "children": { "_process_rank_one_or_two_observation": { "total": 74.58652331002713, "count": 507896, "is_parallel": true, "self": 74.58652331002713 } } } } } } } } } } }, "trainer_advance": { "total": 637.2786827329214, "count": 63488, "self": 2.3541906209611625, "children": { "process_trajectory": { "total": 120.67445461795796, "count": 63488, "self": 120.47950041195872, "children": { "RLTrainer._checkpoint": { "total": 0.19495420599923818, "count": 2, "self": 0.19495420599923818 } } }, "_update_policy": { "total": 514.2500374940023, "count": 452, "self": 287.00432728701117, "children": { "TorchPPOOptimizer.update": { "total": 227.24571020699113, "count": 22746, "self": 227.24571020699113 } } } } } } }, "trainer_threads": { "total": 9.269997462979518e-07, "count": 1, "self": 9.269997462979518e-07 }, "TrainerController._save_models": { "total": 0.08147820199974376, "count": 1, "self": 0.001236320000316482, "children": { "RLTrainer._checkpoint": { "total": 0.08024188199942728, "count": 1, "self": 0.08024188199942728 } } } } } } }