一种基于示例轨迹的抽象动作树构造方法  

An Abstract Action Tree Construction Algorithm Based on Demonstration Trajectories

作　　者：王蕾[1] 

机构地区：[1]苏州卫生职业技术学院,江苏苏州215009

出　　处：《计算机与现代化》2016年第6期85-90,共6页Computer and Modernization

基　　金：国家自然科学基金资助项目(61373094)

摘　　要：自动构造抽象动作一直是分层强化学习研究中的关键技术之一。抽象动作链接算法是目前连续任务中自主发现抽象动作的典型算法,但是抽象动作链接算法需要进行很多次的迭代计算,收敛速度较慢。本文提出一种基于示例轨迹的抽象动作树构造算法(ACADT),通过使用一种变点侦测方法,ACADT把每一个轨迹分割成一个抽象动作链。这些从轨迹中分割得到的抽象动作链随后被合并成一棵抽象动作树。实验表明ACADT可以构造成一棵抽象动作树并能够更快收敛。Automatic construction of abstract action is one of the key technologies in hierarchical reinforcement learning. Skill chaining is a typical algorithm for automatically discovery abstract actions in continuous reinforcement learning domains,but the skill chaining algorithm needs to iterate many times and the convergence speed is slow. This paper presents an abstract action tree construction algorithm based on demonstration trajectories（ ACADT）. By using a change point detection method,ACADT segment each trajectory into a chain. The chains obtained from the multiple trajectories are merged into an abstract action tree. Experimental results show that ACADT can construct an abstract action tree and faster convergence.

关 键 词：分层强化学习 示例轨迹 抽象动作 自动构造 机器学习 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]