加强学习(Reinforcement Learning,简称RL)是一种重要的机器学习方法,在机器入规划、分析预测等领域有许多应用。加强学习的任务即是寻找一条策略,为行为者(agent)在一给定状况下产生一个动 Reinforcement Learning (RL) is an important machine learning method and has many applications in machine planning, analysis and prediction. The task of strengthening learning is to find a strategy for the agent to produce a move in a given situation