{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.16162443161010742, "min": 0.15789465606212616, "max": 1.5367339849472046, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4869.4208984375, "min": 4754.52392578125, "max": 46618.36328125, "count": 100 }, "Pyramids.Step.mean": { "value": 2999968.0, "min": 29952.0, "max": 2999968.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999968.0, "min": 29952.0, "max": 2999968.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8118285536766052, "min": -0.11502286791801453, "max": 0.8630164861679077, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 243.54856872558594, "min": -27.835533142089844, "max": 258.9049377441406, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.022703945636749268, "min": -0.04616357758641243, "max": 0.20310497283935547, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -6.811183929443359, "min": -13.110455513000488, "max": 48.74519348144531, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06751976936218507, "min": 0.06459627301678882, "max": 0.07357598580176397, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9452767710705909, "min": 0.494947158982248, "max": 1.0926436143744664, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011672002123391612, "min": 0.0007036268415791142, "max": 0.016515563614006124, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.16340802972748256, "min": 0.00767740097599644, "max": 0.2316692368137107, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4294352378404776e-06, "min": 1.4294352378404776e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.0012093329766686e-05, "min": 2.0012093329766686e-05, "max": 0.003927291590902833, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10047644523809525, "min": 0.10047644523809525, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4066702333333334, "min": 1.3897045333333333, "max": 2.7674720000000006, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.759687928571435e-05, "min": 5.759687928571435e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008063563100000009, "min": 0.0008063563100000009, "max": 0.13091880695000002, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005666096694767475, "min": 0.005666096694767475, "max": 0.3774621784687042, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.0793253555893898, "min": 0.0793253555893898, "max": 2.642235279083252, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 214.74436090225564, "min": 214.74436090225564, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28561.0, "min": 15984.0, "max": 34359.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7551669014015592, "min": -1.0000000521540642, "max": 1.7694384534771626, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 233.43719788640738, "min": -32.000001668930054, "max": 237.95739808678627, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7551669014015592, "min": -1.0000000521540642, "max": 1.7694384534771626, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 233.43719788640738, "min": -32.000001668930054, "max": 237.95739808678627, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.012531701085379581, "min": 0.012531701085379581, "max": 7.303899978287518, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.6667162443554844, "min": 1.6667162443554844, "max": 116.86239965260029, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1693497343", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/yaohua/miniconda3/envs/drl/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": "2.1.0.dev20230830", "numpy_version": "1.21.2", "end_time_seconds": "1693500008" }, "total": 2664.4789828110006, "count": 1, "self": 0.21767440300209273, "children": { "run_training.setup": { "total": 0.011569790998692042, "count": 1, "self": 0.011569790998692042 }, "TrainerController.start_learning": { "total": 2664.249738617, "count": 1, "self": 3.3313670061725134, "children": { "TrainerController._reset_env": { "total": 1.0220517290017597, "count": 1, "self": 1.0220517290017597 }, "TrainerController.advance": { "total": 2659.864983788828, "count": 194780, "self": 2.862759061896213, "children": { "env_step": { "total": 1742.7104669646633, "count": 194780, "self": 1573.8326645859033, "children": { "SubprocessEnvManager._take_step": { "total": 166.86263520575085, "count": 194780, "self": 8.07827265209744, "children": { "TorchPolicy.evaluate": { "total": 158.7843625536534, "count": 187562, "self": 158.7843625536534 } } }, "workers": { "total": 2.015167173009104, "count": 194780, "self": 0.0, "children": { "worker_root": { "total": 2660.5570696709274, "count": 194780, "is_parallel": true, "self": 1266.3296328622127, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008461830002488568, "count": 1, "is_parallel": true, "self": 0.00025939800252672285, "children": { "_process_rank_one_or_two_observation": { "total": 0.000586784997722134, "count": 8, "is_parallel": true, "self": 0.000586784997722134 } } }, "UnityEnvironment.step": { "total": 0.019954175000748364, "count": 1, "is_parallel": true, "self": 0.00018957599968416616, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00017926000145962462, "count": 1, "is_parallel": true, "self": 0.00017926000145962462 }, "communicator.exchange": { "total": 0.018965930999911507, "count": 1, "is_parallel": true, "self": 0.018965930999911507 }, "steps_from_proto": { "total": 0.0006194079996930668, "count": 1, "is_parallel": true, "self": 0.0002009269992413465, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004184810004517203, "count": 8, "is_parallel": true, "self": 0.0004184810004517203 } } } } } } }, "UnityEnvironment.step": { "total": 1394.2274368087146, "count": 194779, "is_parallel": true, "self": 34.919017709424224, "children": { "UnityEnvironment._generate_step_input": { "total": 22.9513969758882, "count": 194779, "is_parallel": true, "self": 22.9513969758882 }, "communicator.exchange": { "total": 1236.4488385992954, "count": 194779, "is_parallel": true, "self": 1236.4488385992954 }, "steps_from_proto": { "total": 99.90818352410679, "count": 194779, "is_parallel": true, "self": 23.39289753889898, "children": { "_process_rank_one_or_two_observation": { "total": 76.51528598520781, "count": 1558232, "is_parallel": true, "self": 76.51528598520781 } } } } } } } } } } }, "trainer_advance": { "total": 914.2917577622684, "count": 194780, "self": 6.194111263965169, "children": { "process_trajectory": { "total": 171.4765753683223, "count": 194780, "self": 171.29447548532335, "children": { "RLTrainer._checkpoint": { "total": 0.18209988299895485, "count": 6, "self": 0.18209988299895485 } } }, "_update_policy": { "total": 736.6210711299809, "count": 1392, "self": 414.6348139058009, "children": { "TorchPPOOptimizer.update": { "total": 321.98625722418, "count": 68442, "self": 321.98625722418 } } } } } } }, "trainer_threads": { "total": 5.319998308550566e-07, "count": 1, "self": 5.319998308550566e-07 }, "TrainerController._save_models": { "total": 0.031335560997831635, "count": 1, "self": 0.00083905099745607, "children": { "RLTrainer._checkpoint": { "total": 0.030496510000375565, "count": 1, "self": 0.030496510000375565 } } } } } } }