在各种非线性系统中，倒立摆是一典型例子，用强化学习实现控制倒立摆-on-line learning control by association and reinforcement

Q 学习方面的MATLAB程序，对于研究强化学习和自适应动态规划的朋友很有参考价值-Q learning MATLAB. For the study of reinforcement learning and adaptive dynamic programming

时序差分学习是强化学习的一种重要算法，该代码提供了时序差分学习做路径规划的一个仿真。-Temporal difference learning is an important algorithm for reinforcement learning, which provides a simulation of sequential differential learning for path planning.

DQN实现matlab强化学习，解决倒立摆问题(Dqn realizes matlab to strengthen learning and solve the problem of inverted pendulum)