{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5615555644035339, "min": 0.5575332641601562, "max": 1.4418917894363403, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16720.87890625, "min": 16720.87890625, "max": 43741.23046875, "count": 33 }, "Pyramids.Step.mean": { "value": 989954.0, "min": 29934.0, "max": 989954.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989954.0, "min": 29934.0, "max": 989954.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4908810555934906, "min": -0.2482738196849823, "max": 0.4908810555934906, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 134.01052856445312, "min": -58.84089660644531, "max": 134.01052856445312, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.18048235774040222, "min": -0.06717043370008469, "max": 0.2645304203033447, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 49.27168273925781, "min": -17.8001651763916, "max": 63.487300872802734, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07065648124781936, "min": 0.06458748826987269, "max": 0.07310087637334864, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.989190737469471, "min": 0.5548138253556618, "max": 1.0711004963554396, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.024175926813595216, "min": 0.0014057098657258827, "max": 0.024175926813595216, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.33846297539033304, "min": 0.01799983360799972, "max": 0.33846297539033304, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.600040323828569e-06, "min": 7.600040323828569e-06, "max": 0.000294842026719325, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010640056453359997, "min": 0.00010640056453359997, "max": 0.0036088254970581997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025333142857143, "min": 0.1025333142857143, "max": 0.19828067500000002, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354664000000001, "min": 1.4354664000000001, "max": 2.5694593, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002630780971428571, "min": 0.0002630780971428571, "max": 0.0098282394325, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003683093359999999, "min": 0.003683093359999999, "max": 0.12030388582000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009422557428479195, "min": 0.008676164783537388, "max": 0.4038880467414856, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13191580772399902, "min": 0.12146630138158798, "max": 3.2311043739318848, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 399.6707317073171, "min": 399.6707317073171, "max": 998.9375, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32773.0, "min": 16477.0, "max": 32773.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5258394833884121, "min": -0.937368803890422, "max": 1.5258394833884121, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 123.59299815446138, "min": -29.995801724493504, "max": 123.59299815446138, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5258394833884121, "min": -0.937368803890422, "max": 1.5258394833884121, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 123.59299815446138, "min": -29.995801724493504, "max": 123.59299815446138, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03880632835667419, "min": 0.03880632835667419, "max": 7.4559591123286415, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1433125968906097, "min": 2.59506837913068, "max": 126.7513049095869, "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": "1685541119", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1685544324" }, "total": 3205.251565461, "count": 1, "self": 0.5919918469999175, "children": { "run_training.setup": { "total": 0.09185065999997732, "count": 1, "self": 0.09185065999997732 }, "TrainerController.start_learning": { "total": 3204.567722954, "count": 1, "self": 2.373566274989116, "children": { "TrainerController._reset_env": { "total": 1.4379054199999928, "count": 1, "self": 1.4379054199999928 }, "TrainerController.advance": { "total": 3200.6391955030113, "count": 63591, "self": 2.454261158065947, "children": { "env_step": { "total": 2057.724929087961, "count": 63591, "self": 1916.861226287026, "children": { "SubprocessEnvManager._take_step": { "total": 139.33535961700238, "count": 63591, "self": 7.042721024984644, "children": { "TorchPolicy.evaluate": { "total": 132.29263859201774, "count": 62559, "self": 132.29263859201774 } } }, "workers": { "total": 1.5283431839324066, "count": 63591, "self": 0.0, "children": { "worker_root": { "total": 3197.830950685959, "count": 63591, "is_parallel": true, "self": 1459.7216970189334, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007620687999974507, "count": 1, "is_parallel": true, "self": 0.005589987999996993, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020306999999775144, "count": 8, "is_parallel": true, "self": 0.0020306999999775144 } } }, "UnityEnvironment.step": { "total": 0.0618143860000373, "count": 1, "is_parallel": true, "self": 0.0006967660001464537, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00038816099993255193, "count": 1, "is_parallel": true, "self": 0.00038816099993255193 }, "communicator.exchange": { "total": 0.05852409900001021, "count": 1, "is_parallel": true, "self": 0.05852409900001021 }, "steps_from_proto": { "total": 0.0022053599999480866, "count": 1, "is_parallel": true, "self": 0.00046366000003672525, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017416999999113614, "count": 8, "is_parallel": true, "self": 0.0017416999999113614 } } } } } } }, "UnityEnvironment.step": { "total": 1738.1092536670258, "count": 63590, "is_parallel": true, "self": 48.37754291311194, "children": { "UnityEnvironment._generate_step_input": { "total": 26.71554404390929, "count": 63590, "is_parallel": true, "self": 26.71554404390929 }, "communicator.exchange": { "total": 1525.1164294810135, "count": 63590, "is_parallel": true, "self": 1525.1164294810135 }, "steps_from_proto": { "total": 137.89973722899106, "count": 63590, "is_parallel": true, "self": 29.46247766308545, "children": { "_process_rank_one_or_two_observation": { "total": 108.4372595659056, "count": 508720, "is_parallel": true, "self": 108.4372595659056 } } } } } } } } } } }, "trainer_advance": { "total": 1140.4600052569845, "count": 63591, "self": 4.885910436054019, "children": { "process_trajectory": { "total": 146.3367421679302, "count": 63591, "self": 145.9549857109307, "children": { "RLTrainer._checkpoint": { "total": 0.3817564569994829, "count": 2, "self": 0.3817564569994829 } } }, "_update_policy": { "total": 989.2373526530001, "count": 456, "self": 428.6808045020081, "children": { "TorchPPOOptimizer.update": { "total": 560.5565481509921, "count": 22797, "self": 560.5565481509921 } } } } } } }, "trainer_threads": { "total": 1.4060001376492437e-06, "count": 1, "self": 1.4060001376492437e-06 }, "TrainerController._save_models": { "total": 0.11705434999976205, "count": 1, "self": 0.0015564869995614572, "children": { "RLTrainer._checkpoint": { "total": 0.1154978630002006, "count": 1, "self": 0.1154978630002006 } } } } } } }