{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7579878568649292, "min": 0.6082875728607178, "max": 1.448693037033081, "count": 16 }, "Pyramids.Policy.Entropy.sum": { "value": 22800.275390625, "min": 17791.1953125, "max": 43947.55078125, "count": 16 }, "Pyramids.Step.mean": { "value": 479894.0, "min": 29952.0, "max": 479894.0, "count": 16 }, "Pyramids.Step.sum": { "value": 479894.0, "min": 29952.0, "max": 479894.0, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.07348731905221939, "min": -0.1460859626531601, "max": -0.02258189395070076, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -17.6369571685791, "min": -34.622371673583984, "max": -5.442236423492432, "count": 16 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02711433544754982, "min": 0.02525223232805729, "max": 0.3571232855319977, "count": 16 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.507440567016602, "min": 6.085787773132324, "max": 84.63822174072266, "count": 16 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07035029758043791, "min": 0.0661739269676664, "max": 0.07172009596808034, "count": 16 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9849041661261309, "min": 0.48547021068676766, "max": 0.9946436752322311, "count": 16 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.000834662312260333, "min": 0.00031523870841881376, "max": 0.0065712490545257, "count": 16 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.011685272371644661, "min": 0.003782864501025765, "max": 0.053147435931653796, "count": 16 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.0766264506514284e-05, "min": 2.0766264506514284e-05, "max": 0.00029030126037577137, "count": 16 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00029072770309119996, "min": 0.00029072770309119996, "max": 0.0026353767215412, "count": 16 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10692205714285717, "min": 0.10692205714285717, "max": 0.19676708571428575, "count": 16 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4969088000000004, "min": 1.3773696000000002, "max": 2.0784588000000004, "count": 16 }, "Pyramids.Policy.Beta.mean": { "value": 0.0007015135085714285, "min": 0.0007015135085714285, "max": 0.00967703186285714, "count": 16 }, "Pyramids.Policy.Beta.sum": { "value": 0.009821189119999999, "min": 0.009821189119999999, "max": 0.08787803412000002, "count": 16 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.02401557005941868, "min": 0.02401557005941868, "max": 0.4124005138874054, "count": 16 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.3362179696559906, "min": 0.3362179696559906, "max": 2.88680362701416, "count": 16 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 983.4375, "min": 833.5, "max": 999.0, "count": 16 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31470.0, "min": 15984.0, "max": 33307.0, "count": 16 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.8590250513516366, "min": -1.0000000521540642, "max": -0.2507500406354666, "count": 16 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -27.488801643252373, "min": -31.99920167028904, "max": -6.018000975251198, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.8590250513516366, "min": -1.0000000521540642, "max": -0.2507500406354666, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -27.488801643252373, "min": -31.99920167028904, "max": -6.018000975251198, "count": 16 }, "Pyramids.Policy.RndReward.mean": { "value": 0.24201162983081304, "min": 0.24201162983081304, "max": 7.885494565591216, "count": 16 }, "Pyramids.Policy.RndReward.sum": { "value": 7.744372154586017, "min": 7.744372154586017, "max": 126.16791304945946, "count": 16 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1681293732", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1681294706" }, "total": 974.007467129, "count": 1, "self": 0.5477050630001941, "children": { "run_training.setup": { "total": 0.11668722399997478, "count": 1, "self": 0.11668722399997478 }, "TrainerController.start_learning": { "total": 973.3430748419999, "count": 1, "self": 0.6759002000075043, "children": { "TrainerController._reset_env": { "total": 4.063474004999989, "count": 1, "self": 4.063474004999989 }, "TrainerController.advance": { "total": 968.5083623919924, "count": 31511, "self": 0.6883046399979094, "children": { "env_step": { "total": 663.3104763319949, "count": 31511, "self": 610.5543238240207, "children": { "SubprocessEnvManager._take_step": { "total": 52.34823230698407, "count": 31511, "self": 2.3505269959886164, "children": { "TorchPolicy.evaluate": { "total": 49.99770531099546, "count": 31304, "self": 49.99770531099546 } } }, "workers": { "total": 0.40792020099007686, "count": 31511, "self": 0.0, "children": { "worker_root": { "total": 971.0200774940174, "count": 31511, "is_parallel": true, "self": 414.67753474100573, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004816813999980241, "count": 1, "is_parallel": true, "self": 0.0035615759999814145, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012552379999988261, "count": 8, "is_parallel": true, "self": 0.0012552379999988261 } } }, "UnityEnvironment.step": { "total": 0.07777846400000499, "count": 1, "is_parallel": true, "self": 0.0025735670000130995, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004756429999588363, "count": 1, "is_parallel": true, "self": 0.0004756429999588363 }, "communicator.exchange": { "total": 0.0730688180000243, "count": 1, "is_parallel": true, "self": 0.0730688180000243 }, "steps_from_proto": { "total": 0.0016604360000087581, "count": 1, "is_parallel": true, "self": 0.0003779680000661756, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012824679999425825, "count": 8, "is_parallel": true, "self": 0.0012824679999425825 } } } } } } }, "UnityEnvironment.step": { "total": 556.3425427530117, "count": 31510, "is_parallel": true, "self": 16.367329631991083, "children": { "UnityEnvironment._generate_step_input": { "total": 11.473071650002282, "count": 31510, "is_parallel": true, "self": 11.473071650002282 }, "communicator.exchange": { "total": 481.73043130901266, "count": 31510, "is_parallel": true, "self": 481.73043130901266 }, "steps_from_proto": { "total": 46.77171016200566, "count": 31510, "is_parallel": true, "self": 9.849368285999674, "children": { "_process_rank_one_or_two_observation": { "total": 36.92234187600599, "count": 252080, "is_parallel": true, "self": 36.92234187600599 } } } } } } } } } } }, "trainer_advance": { "total": 304.5095814199995, "count": 31511, "self": 1.0428892009993547, "children": { "process_trajectory": { "total": 51.15358043199831, "count": 31511, "self": 51.039550797998345, "children": { "RLTrainer._checkpoint": { "total": 0.11402963399996224, "count": 1, "self": 0.11402963399996224 } } }, "_update_policy": { "total": 252.31311178700184, "count": 200, "self": 161.73627050800786, "children": { "TorchPPOOptimizer.update": { "total": 90.57684127899398, "count": 11445, "self": 90.57684127899398 } } } } } } }, "trainer_threads": { "total": 9.259999842470279e-07, "count": 1, "self": 9.259999842470279e-07 }, "TrainerController._save_models": { "total": 0.0953373190000093, "count": 1, "self": 0.001378044999910344, "children": { "RLTrainer._checkpoint": { "total": 0.09395927400009896, "count": 1, "self": 0.09395927400009896 } } } } } } }