强化学习是人工智能基本的子领域之一，在强化学习的框架中，智能体通过与环境互动，来学习采取何种动作能使其在给定环境中的长期奖励最大化，就像在上述的棋盘游戏寓言中，你通过与棋盘的互动来学习。

书籍：《REINFORCEMENT LEARNING AND STOCHASTIC OPTIMIZATION》


作者：Warren B. Powell
Warren B. Powell is a faculty member of the Department of Operations Research and Financial Engineering at Princeton University.

简介：This book is not intended to replace the much more thorough treatments of the more
specialized books that focus on specific modeling approaches and algorithmic strategies.
Rather, our goal is to provide a unified framework that provides a more comprehensive
perspective of these fields. We have found that a single problem can be reasonably
approached by techniques from multiple fields such as dynamic programming (operations
research), model predictive control (control theory) and policy search (computer science),
where any one of these methods may work best, depending on the specific characteristics
of the data. At the same time, powerful hybrid strategies can be created by combining the
tools from different fields.