{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4650466740131378, "min": 0.45198699831962585, "max": 1.3714216947555542, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13936.5185546875, "min": 13523.451171875, "max": 41603.44921875, "count": 33 }, "Pyramids.Step.mean": { "value": 989987.0, "min": 29995.0, "max": 989987.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989987.0, "min": 29995.0, "max": 989987.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4839240312576294, "min": -0.10781673341989517, "max": 0.5328575372695923, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 133.5630340576172, "min": -25.87601661682129, "max": 147.0686798095703, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03618714585900307, "min": -0.03157714009284973, "max": 0.3045389950275421, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.987651824951172, "min": -8.620559692382812, "max": 72.48027801513672, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06936236379052778, "min": 0.06410990634046793, "max": 0.07731013668221778, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.971073093067389, "min": 0.6184810934577423, "max": 1.0888817973318508, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016985429242292106, "min": 0.00019329929413792703, "max": 0.016985429242292106, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2377960093920895, "min": 0.0025128908237930514, "max": 0.2377960093920895, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.65839030437857e-06, "min": 7.65839030437857e-06, "max": 0.0002948495642168125, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010721746426129998, "min": 0.00010721746426129998, "max": 0.0034926391357869998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255276428571428, "min": 0.10255276428571428, "max": 0.19828318749999999, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4357387, "min": 1.4357387, "max": 2.5276007, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002650211521428571, "min": 0.0002650211521428571, "max": 0.00982849043125, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037102961299999996, "min": 0.0037102961299999996, "max": 0.1164348787, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011340792290866375, "min": 0.011340792290866375, "max": 0.38198626041412354, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1587710976600647, "min": 0.1587710976600647, "max": 3.0558900833129883, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 364.1566265060241, "min": 362.0394736842105, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30225.0, "min": 16410.0, "max": 33760.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5899618790440617, "min": -0.9999250522814691, "max": 1.604392386218415, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 133.55679783970118, "min": -31.99760167300701, "max": 133.55679783970118, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5899618790440617, "min": -0.9999250522814691, "max": 1.604392386218415, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 133.55679783970118, "min": -31.99760167300701, "max": 133.55679783970118, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.043156246275040236, "min": 0.043156246275040236, "max": 8.022046904353534, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.62512468710338, "min": 3.459988677801448, "max": 136.3747973740101, "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": "1788730448", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1788732765" }, "total": 2317.6280874060003, "count": 1, "self": 0.7350097270009428, "children": { "run_training.setup": { "total": 0.033886544999859325, "count": 1, "self": 0.033886544999859325 }, "TrainerController.start_learning": { "total": 2316.8591911339995, "count": 1, "self": 1.3624061329715005, "children": { "TrainerController._reset_env": { "total": 2.2390712769997663, "count": 1, "self": 2.2390712769997663 }, "TrainerController.advance": { "total": 2313.1484870850286, "count": 63599, "self": 1.442036209994967, "children": { "env_step": { "total": 1680.8450035859987, "count": 63599, "self": 1530.7138123560107, "children": { "SubprocessEnvManager._take_step": { "total": 149.34583671103792, "count": 63599, "self": 4.65264065106112, "children": { "TorchPolicy.evaluate": { "total": 144.6931960599768, "count": 62552, "self": 144.6931960599768 } } }, "workers": { "total": 0.7853545189500437, "count": 63599, "self": 0.0, "children": { "worker_root": { "total": 2311.0344135950418, "count": 63599, "is_parallel": true, "self": 896.058109232169, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017086059997382108, "count": 1, "is_parallel": true, "self": 0.0005795279998892511, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011290779998489597, "count": 8, "is_parallel": true, "self": 0.0011290779998489597 } } }, "UnityEnvironment.step": { "total": 0.05082458900005804, "count": 1, "is_parallel": true, "self": 0.000547662000371929, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004610149999280111, "count": 1, "is_parallel": true, "self": 0.0004610149999280111 }, "communicator.exchange": { "total": 0.048280236999744375, "count": 1, "is_parallel": true, "self": 0.048280236999744375 }, "steps_from_proto": { "total": 0.0015356750000137254, "count": 1, "is_parallel": true, "self": 0.0003140380003969767, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012216369996167487, "count": 8, "is_parallel": true, "self": 0.0012216369996167487 } } } } } } }, "UnityEnvironment.step": { "total": 1414.9763043628727, "count": 63598, "is_parallel": true, "self": 33.9748706518435, "children": { "UnityEnvironment._generate_step_input": { "total": 23.514443915022184, "count": 63598, "is_parallel": true, "self": 23.514443915022184 }, "communicator.exchange": { "total": 1249.2258477360465, "count": 63598, "is_parallel": true, "self": 1249.2258477360465 }, "steps_from_proto": { "total": 108.26114205996055, "count": 63598, "is_parallel": true, "self": 22.752200541086495, "children": { "_process_rank_one_or_two_observation": { "total": 85.50894151887405, "count": 508784, "is_parallel": true, "self": 85.50894151887405 } } } } } } } } } } }, "trainer_advance": { "total": 630.8614472890349, "count": 63599, "self": 2.5172654760235673, "children": { "process_trajectory": { "total": 111.5168112960132, "count": 63599, "self": 111.28595478401303, "children": { "RLTrainer._checkpoint": { "total": 0.2308565120001731, "count": 2, "self": 0.2308565120001731 } } }, "_update_policy": { "total": 516.8273705169981, "count": 453, "self": 276.0610541869801, "children": { "TorchPPOOptimizer.update": { "total": 240.76631633001807, "count": 22794, "self": 240.76631633001807 } } } } } } }, "trainer_threads": { "total": 1.1659994925139472e-06, "count": 1, "self": 1.1659994925139472e-06 }, "TrainerController._save_models": { "total": 0.1092254730001514, "count": 1, "self": 0.0013349040009416058, "children": { "RLTrainer._checkpoint": { "total": 0.10789056899920979, "count": 1, "self": 0.10789056899920979 } } } } } } }