{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5860971808433533, "min": 0.529802143573761, "max": 1.4659568071365356, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17554.783203125, "min": 15885.5869140625, "max": 44471.265625, "count": 33 }, "Pyramids.Step.mean": { "value": 989912.0, "min": 29949.0, "max": 989912.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989912.0, "min": 29949.0, "max": 989912.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.24384678900241852, "min": -0.11365663260221481, "max": 0.33754763007164, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 61.6932373046875, "min": -27.277591705322266, "max": 88.09992980957031, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.05738731101155281, "min": 0.0020326466765254736, "max": 0.44302111864089966, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 14.518989562988281, "min": 0.5101943016052246, "max": 104.99600219726562, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06838485220560826, "min": 0.06457796609641686, "max": 0.0750269215382945, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9573879308785156, "min": 0.5924547294634023, "max": 1.0399803047184832, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011874307067219411, "min": 7.24033195279153e-05, "max": 0.013406020514764683, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.16624029894107176, "min": 0.0009412431538628989, "max": 0.18768428720670557, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.326633272107144e-06, "min": 7.326633272107144e-06, "max": 0.00029499405166864996, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010257286580950002, "min": 0.00010257286580950002, "max": 0.0033317832894055994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244217857142858, "min": 0.10244217857142858, "max": 0.19833135, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4341905000000001, "min": 1.4341905000000001, "max": 2.3105944, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002539736392857143, "min": 0.0002539736392857143, "max": 0.009833301865000001, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035556309500000007, "min": 0.0035556309500000007, "max": 0.11106838056000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012800812721252441, "min": 0.012800812721252441, "max": 0.571499228477478, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17921137809753418, "min": 0.17921137809753418, "max": 4.571993827819824, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 617.4893617021277, "min": 525.1034482758621, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29022.0, "min": 16236.0, "max": 32562.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.8717489031718132, "min": -0.9999355361346276, "max": 1.1822414717303131, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 40.97219844907522, "min": -31.99760167300701, "max": 65.53839886933565, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.8717489031718132, "min": -0.9999355361346276, "max": 1.1822414717303131, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 40.97219844907522, "min": -31.99760167300701, "max": 65.53839886933565, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08254484907832947, "min": 0.076731146935219, "max": 12.424671081935658, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.8796079066814855, "min": 3.8796079066814855, "max": 211.2194083929062, "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": "1681132230", "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 Training2 --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": "1681134244" }, "total": 2014.0702878639995, "count": 1, "self": 0.7861269909990369, "children": { "run_training.setup": { "total": 0.11439756500021758, "count": 1, "self": 0.11439756500021758 }, "TrainerController.start_learning": { "total": 2013.1697633080003, "count": 1, "self": 1.4625661499749185, "children": { "TrainerController._reset_env": { "total": 3.721074891000171, "count": 1, "self": 3.721074891000171 }, "TrainerController.advance": { "total": 2007.8372440420253, "count": 63217, "self": 1.4880243100160442, "children": { "env_step": { "total": 1397.8733434619735, "count": 63217, "self": 1290.2501676658976, "children": { "SubprocessEnvManager._take_step": { "total": 106.77144864707043, "count": 63217, "self": 4.641087374026938, "children": { "TorchPolicy.evaluate": { "total": 102.13036127304349, "count": 62566, "self": 102.13036127304349 } } }, "workers": { "total": 0.8517271490054554, "count": 63217, "self": 0.0, "children": { "worker_root": { "total": 2008.2002263690574, "count": 63217, "is_parallel": true, "self": 828.0216600810581, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001642557999730343, "count": 1, "is_parallel": true, "self": 0.0005171910006538383, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011253669990765047, "count": 8, "is_parallel": true, "self": 0.0011253669990765047 } } }, "UnityEnvironment.step": { "total": 0.0471700010002678, "count": 1, "is_parallel": true, "self": 0.0007109070002115914, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005044330000600894, "count": 1, "is_parallel": true, "self": 0.0005044330000600894 }, "communicator.exchange": { "total": 0.04426920100013376, "count": 1, "is_parallel": true, "self": 0.04426920100013376 }, "steps_from_proto": { "total": 0.0016854599998623598, "count": 1, "is_parallel": true, "self": 0.000400528998397931, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012849310014644288, "count": 8, "is_parallel": true, "self": 0.0012849310014644288 } } } } } } }, "UnityEnvironment.step": { "total": 1180.1785662879993, "count": 63216, "is_parallel": true, "self": 32.21203886411604, "children": { "UnityEnvironment._generate_step_input": { "total": 22.331103760920996, "count": 63216, "is_parallel": true, "self": 22.331103760920996 }, "communicator.exchange": { "total": 1033.053226411861, "count": 63216, "is_parallel": true, "self": 1033.053226411861 }, "steps_from_proto": { "total": 92.5821972511012, "count": 63216, "is_parallel": true, "self": 19.971862813059488, "children": { "_process_rank_one_or_two_observation": { "total": 72.61033443804172, "count": 505728, "is_parallel": true, "self": 72.61033443804172 } } } } } } } } } } }, "trainer_advance": { "total": 608.4758762700358, "count": 63217, "self": 2.510810965040946, "children": { "process_trajectory": { "total": 101.3024001099975, "count": 63217, "self": 101.03079514699766, "children": { "RLTrainer._checkpoint": { "total": 0.27160496299984516, "count": 2, "self": 0.27160496299984516 } } }, "_update_policy": { "total": 504.6626651949973, "count": 439, "self": 324.49201686602373, "children": { "TorchPPOOptimizer.update": { "total": 180.17064832897358, "count": 22851, "self": 180.17064832897358 } } } } } } }, "trainer_threads": { "total": 1.5010000424808823e-06, "count": 1, "self": 1.5010000424808823e-06 }, "TrainerController._save_models": { "total": 0.14887672399981966, "count": 1, "self": 0.0019089959996563266, "children": { "RLTrainer._checkpoint": { "total": 0.14696772800016333, "count": 1, "self": 0.14696772800016333 } } } } } } }