搜索资源列表
maze
- 经典的迷宫问题 可用于对强化学习最优路径的研究-The classic maze can be used to study the optimal path reinforcement learning
migong
- 使用Qlearing实现基本的走迷宫游戏(Using Qlearing to achieve maze game)
ReinforcementLearning
- 用强化学习方法解决简单的走迷宫问题，得到智能体的最优路径(Using reinforcement learning to solve simple maze problem)
RL
- 用python搭建了各类常用的强化学习算法的框架，通过迷宫寻路的例子实现各类算法。(The fr a mework of all kinds of commonly used reinforcement learning algorithms is built with Python, and all kinds of algorithms are realized by the example of labyrinth finding
rl
- python实现强化学习，基于吴恩达教程，实现机器人自动走迷宫功能(Python implementation of reinforcement learning)
Dyna-H
- 设定动态仿真环境，环境为动态随机游戏，用于寻找最优路径(Use to find the optimal path)