{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3170534372329712, "min": 0.3170534372329712, "max": 1.423827052116394, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9567.404296875, "min": 9494.548828125, "max": 43193.21875, "count": 33 }, "Pyramids.Step.mean": { "value": 989939.0, "min": 29886.0, "max": 989939.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989939.0, "min": 29886.0, "max": 989939.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.37809258699417114, "min": -0.09256956726312637, "max": 0.37809258699417114, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 98.68216705322266, "min": -22.30926513671875, "max": 101.30860900878906, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.043712910264730453, "min": -0.15976057946681976, "max": 0.4693271815776825, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 11.409070014953613, "min": -42.65607452392578, "max": 111.23054504394531, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07068945088788034, "min": 0.0637067159030786, "max": 0.07266380958613243, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9896523124303248, "min": 0.49792798452150216, "max": 1.060968734139654, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012487380566522684, "min": 0.0006170832158190465, "max": 0.021231653219036247, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17482332793131758, "min": 0.006787915374009511, "max": 0.29724314506650745, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.605290322078576e-06, "min": 7.605290322078576e-06, "max": 0.0002952357444452286, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010647406450910006, "min": 0.00010647406450910006, "max": 0.0035087657304115, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253506428571428, "min": 0.10253506428571428, "max": 0.19841191428571428, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354909, "min": 1.3888833999999999, "max": 2.5695885, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002632529221428573, "min": 0.0002632529221428573, "max": 0.009841350237142856, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036855409100000026, "min": 0.0036855409100000026, "max": 0.11698189115000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.017611611634492874, "min": 0.017611611634492874, "max": 0.5761937499046326, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.24656257033348083, "min": 0.24656257033348083, "max": 4.033356189727783, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 487.9047619047619, "min": 426.2, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30738.0, "min": 16685.0, "max": 32127.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2299515894584117, "min": -0.9999548908202879, "max": 1.3746028263654029, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 76.25699854642153, "min": -30.998601615428925, "max": 96.2221978455782, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2299515894584117, "min": -0.9999548908202879, "max": 1.3746028263654029, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 76.25699854642153, "min": -30.998601615428925, "max": 96.2221978455782, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.085979438468536, "min": 0.07873132467502728, "max": 11.024807128836127, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.330725185049232, "min": 5.117536103876773, "max": 187.42172119021416, "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": "1707161220", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1707163321" }, "total": 2100.6536982589996, "count": 1, "self": 0.488728669000011, "children": { "run_training.setup": { "total": 0.04702223499998581, "count": 1, "self": 0.04702223499998581 }, "TrainerController.start_learning": { "total": 2100.1179473549996, "count": 1, "self": 1.2642461869431827, "children": { "TrainerController._reset_env": { "total": 2.31971016100033, "count": 1, "self": 2.31971016100033 }, "TrainerController.advance": { "total": 2096.4452197230557, "count": 63506, "self": 1.4146450511279909, "children": { "env_step": { "total": 1478.5633234219704, "count": 63506, "self": 1350.9761534170402, "children": { "SubprocessEnvManager._take_step": { "total": 126.78121090198465, "count": 63506, "self": 4.601796020991969, "children": { "TorchPolicy.evaluate": { "total": 122.17941488099268, "count": 62562, "self": 122.17941488099268 } } }, "workers": { "total": 0.8059591029455078, "count": 63506, "self": 0.0, "children": { "worker_root": { "total": 2095.1081836669914, "count": 63506, "is_parallel": true, "self": 855.5071973320023, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002019509000092512, "count": 1, "is_parallel": true, "self": 0.0006746029998794256, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013449060002130864, "count": 8, "is_parallel": true, "self": 0.0013449060002130864 } } }, "UnityEnvironment.step": { "total": 0.047629562000111036, "count": 1, "is_parallel": true, "self": 0.0005885919999855105, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004960149999533314, "count": 1, "is_parallel": true, "self": 0.0004960149999533314 }, "communicator.exchange": { "total": 0.044924025000000256, "count": 1, "is_parallel": true, "self": 0.044924025000000256 }, "steps_from_proto": { "total": 0.0016209300001719384, "count": 1, "is_parallel": true, "self": 0.0003406120004001423, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012803179997717962, "count": 8, "is_parallel": true, "self": 0.0012803179997717962 } } } } } } }, "UnityEnvironment.step": { "total": 1239.600986334989, "count": 63505, "is_parallel": true, "self": 34.315034502942126, "children": { "UnityEnvironment._generate_step_input": { "total": 23.619734599997628, "count": 63505, "is_parallel": true, "self": 23.619734599997628 }, "communicator.exchange": { "total": 1085.3892154540044, "count": 63505, "is_parallel": true, "self": 1085.3892154540044 }, "steps_from_proto": { "total": 96.2770017780449, "count": 63505, "is_parallel": true, "self": 18.945499159917745, "children": { "_process_rank_one_or_two_observation": { "total": 77.33150261812716, "count": 508040, "is_parallel": true, "self": 77.33150261812716 } } } } } } } } } } }, "trainer_advance": { "total": 616.4672512499574, "count": 63506, "self": 2.6097869309292037, "children": { "process_trajectory": { "total": 121.17094428303608, "count": 63506, "self": 120.96907913403629, "children": { "RLTrainer._checkpoint": { "total": 0.20186514899978647, "count": 2, "self": 0.20186514899978647 } } }, "_update_policy": { "total": 492.6865200359921, "count": 451, "self": 286.8186106690173, "children": { "TorchPPOOptimizer.update": { "total": 205.8679093669748, "count": 22797, "self": 205.8679093669748 } } } } } } }, "trainer_threads": { "total": 9.540008250041865e-07, "count": 1, "self": 9.540008250041865e-07 }, "TrainerController._save_models": { "total": 0.08877032999953371, "count": 1, "self": 0.001366280000183906, "children": { "RLTrainer._checkpoint": { "total": 0.08740404999934981, "count": 1, "self": 0.08740404999934981 } } } } } } }