{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4450214207172394, "min": 0.4414829909801483, "max": 1.4873738288879395, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13350.642578125, "min": 13223.298828125, "max": 45120.97265625, "count": 33 }, "Pyramids.Step.mean": { "value": 989905.0, "min": 29952.0, "max": 989905.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989905.0, "min": 29952.0, "max": 989905.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.43758314847946167, "min": -0.08327947556972504, "max": 0.5274014472961426, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 117.70986938476562, "min": -19.98707389831543, "max": 145.86622619628906, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.027456559240818024, "min": -0.005989507306367159, "max": 0.3075923025608063, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.385814189910889, "min": -1.641124963760376, "max": 73.82215118408203, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06993176419296397, "min": 0.06492985318942648, "max": 0.07450622633387824, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9790446987014956, "min": 0.48335857376196667, "max": 1.0834755802049996, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013908271566471958, "min": 0.00023015699846647925, "max": 0.015912911667486398, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19471580193060742, "min": 0.002761883981597751, "max": 0.22278076334480956, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.668054586871429e-06, "min": 7.668054586871429e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001073527642162, "min": 0.0001073527642162, "max": 0.003506912931029099, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255598571428572, "min": 0.10255598571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4357838, "min": 1.3691136000000002, "max": 2.5725757, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002653429728571429, "min": 0.0002653429728571429, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037148016200000003, "min": 0.0037148016200000003, "max": 0.11692019291000003, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008492152206599712, "min": 0.008492152206599712, "max": 0.3906228542327881, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11889012902975082, "min": 0.11889012902975082, "max": 2.7343599796295166, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 406.0, "min": 350.8837209302326, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28014.0, "min": 15984.0, "max": 33851.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4755382124772842, "min": -1.0000000521540642, "max": 1.6207585936819, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 100.33659844845533, "min": -32.000001668930054, "max": 141.0059976503253, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4755382124772842, "min": -1.0000000521540642, "max": 1.6207585936819, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 100.33659844845533, "min": -32.000001668930054, "max": 141.0059976503253, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0362502126599258, "min": 0.03262208137785348, "max": 7.670607476495206, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.4650144608749542, "min": 2.4650144608749542, "max": 122.7297196239233, "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": "1706940113", "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": "1706942637" }, "total": 2524.3102444399997, "count": 1, "self": 0.5513084690001051, "children": { "run_training.setup": { "total": 0.04908062399999835, "count": 1, "self": 0.04908062399999835 }, "TrainerController.start_learning": { "total": 2523.7098553469996, "count": 1, "self": 1.9261648489432446, "children": { "TrainerController._reset_env": { "total": 3.3156626990003133, "count": 1, "self": 3.3156626990003133 }, "TrainerController.advance": { "total": 2518.366702663057, "count": 63712, "self": 2.045310923051602, "children": { "env_step": { "total": 1842.2226173470312, "count": 63712, "self": 1679.0862757477557, "children": { "SubprocessEnvManager._take_step": { "total": 161.9514966281472, "count": 63712, "self": 5.78313609812767, "children": { "TorchPolicy.evaluate": { "total": 156.16836053001953, "count": 62555, "self": 156.16836053001953 } } }, "workers": { "total": 1.1848449711283138, "count": 63712, "self": 0.0, "children": { "worker_root": { "total": 2517.3256653120266, "count": 63712, "is_parallel": true, "self": 983.6260426450272, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005608111999663379, "count": 1, "is_parallel": true, "self": 0.004241097999511112, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013670140001522668, "count": 8, "is_parallel": true, "self": 0.0013670140001522668 } } }, "UnityEnvironment.step": { "total": 0.05333102400027201, "count": 1, "is_parallel": true, "self": 0.0006964350009184272, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005291359998409462, "count": 1, "is_parallel": true, "self": 0.0005291359998409462 }, "communicator.exchange": { "total": 0.050261448999663116, "count": 1, "is_parallel": true, "self": 0.050261448999663116 }, "steps_from_proto": { "total": 0.0018440039998495195, "count": 1, "is_parallel": true, "self": 0.0003815269997176074, "children": { "_process_rank_one_or_two_observation": { "total": 0.001462477000131912, "count": 8, "is_parallel": true, "self": 0.001462477000131912 } } } } } } }, "UnityEnvironment.step": { "total": 1533.6996226669994, "count": 63711, "is_parallel": true, "self": 41.879836477938625, "children": { "UnityEnvironment._generate_step_input": { "total": 28.774569862060616, "count": 63711, "is_parallel": true, "self": 28.774569862060616 }, "communicator.exchange": { "total": 1344.0662955570278, "count": 63711, "is_parallel": true, "self": 1344.0662955570278 }, "steps_from_proto": { "total": 118.97892076997232, "count": 63711, "is_parallel": true, "self": 25.013950079028746, "children": { "_process_rank_one_or_two_observation": { "total": 93.96497069094357, "count": 509688, "is_parallel": true, "self": 93.96497069094357 } } } } } } } } } } }, "trainer_advance": { "total": 674.0987743929741, "count": 63712, "self": 3.670602042016071, "children": { "process_trajectory": { "total": 139.28155945095523, "count": 63712, "self": 139.06700894895494, "children": { "RLTrainer._checkpoint": { "total": 0.2145505020002929, "count": 2, "self": 0.2145505020002929 } } }, "_update_policy": { "total": 531.1466129000028, "count": 445, "self": 310.83162593602174, "children": { "TorchPPOOptimizer.update": { "total": 220.31498696398103, "count": 22800, "self": 220.31498696398103 } } } } } } }, "trainer_threads": { "total": 9.7599968285067e-07, "count": 1, "self": 9.7599968285067e-07 }, "TrainerController._save_models": { "total": 0.10132415999942168, "count": 1, "self": 0.001620691999050905, "children": { "RLTrainer._checkpoint": { "total": 0.09970346800037078, "count": 1, "self": 0.09970346800037078 } } } } } } }