强化学习 Dyna-H算法代码

sarsa,q-learning

function [ actions ] = BuildActionList
%BuildActionList

%actions for the mountain car problem
actions = （1:4）‘;

 属性            大小     日期    时间   名称
----------- ---------  ---------- -----  ----

     文件        113  2010-12-28 00:28  BuildActionList.m

     文件        156  2010-11-21 15:11  BuildModel.m

     文件        147  2010-11-19 21:25  BuildQTable.m

     文件        156  2010-11-21 12:02  BuildStateList.m

     文件        785  2010-11-19 21:18  CreateFigureGrid.m

     文件        400  2010-12-05 14:16  CreateMaze.m

     文件        195  2007-10-08 17:35  DiscretizeState.m

     文件        589  2010-11-21 13:30  DoAction.m

     文件       1918  2011-02-12 00:48  DynaHDemo.m

     文件        426  2010-11-21 14:53  e_greedy_selection.m

     文件        110  2007-10-08 17:35  edist.m

     文件       2159  2011-02-12 00:51  Episode.m

     文件        629  2010-11-25 11:48  GetBestAction.m

     文件        641  2010-11-28 22:16  GetHAction.m

     文件        384  2010-11-28 22:58  GetReward.m

     文件       1077  2010-12-07 22:55  HPlanning.m

     文件         39  2011-02-12 00:42  Main.m

     文件       1156  2010-12-07 20:31  Plot.m

     文件        938  2008-10-22 16:31  setprod.m

     文件        524  2010-11-21 15:05  UpdateModel.m

     文件        589  2010-11-21 15:03  UpdateQLearning.m

     文件        154  2011-02-12 01:17  readme.txt

----------- ---------  ---------- -----  ----

                13285                    22