这个MATLAB的Q-Learning代码是由Ioannis Makris和Andrew Chalikiopoulos编写的。它训练一个特工在一个25×25的迷宫中找到最短的路。随着算法的收敛，MATLAB将打印出到达目标的最短路径，并创建三个图来衡量agent的性能。
This Q-Learning code for MATLAB has been written by Ioannis Makris and Andrew Chalikiopoulos. It trains an agent to find the shortest way through a 25×25 maze. Following convergence of the algorithm, MATLAB will print out the shortest path to the goal and will also create three graphs to measure the performance of the agent.
资源文件列表
Q-Learning-Algorithm-Implementation-in-MATLAB-master/LICENSE , 18047
Q-Learning-Algorithm-Implementation-in-MATLAB-master/README.md , 3677
Q-Learning-Algorithm-Implementation-in-MATLAB-master/RandomPermutation.m , 858
Q-Learning-Algorithm-Implementation-in-MATLAB-master/ReinforcementLearningGreedy.m , 5801
Q-Learning-Algorithm-Implementation-in-MATLAB-master/ReinforcementLearningUpdateR.m , 5921
Q-Learning-Algorithm-Implementation-in-MATLAB-master/ReinforcementLearning_RandomPol.m , 4448
Q-Learning-Algorithm-Implementation-in-MATLAB-master/RewardMatrix100.m , 166
Q-Learning-Algorithm-Implementation-in-MATLAB-master/RewardMatrix25.m , 4046
Q-Learning-Algorithm-Implementation-in-MATLAB-master/RewardMatrixNoPunishment.csv , 49411
Q-Learning-Algorithm-Implementation-in-MATLAB-master/RewardMatrixPunishment.csv , 49284