Learning Action Strategies for Planning Domains Using Genetic Programming
Learning Action Strategies for Planning Domains Using Genetic Programming
复制标题
使用遗传编程规划领域的学习行动策略
DOI：
10.1007/3-540-36605-9_62
复制
发表时间：
2003
期刊：
影响因子：
--
通讯作者：
Dave Humphreys
中科院分区：
文献类型：
--
作者：
J. Levine;Dave Humphreys
有许多不同的方法来解决规划问题，其中之一是使用特定领域的控制知识，以帮助指导领域独立的搜索算法。本文介绍了L2计划，它表示这种控制知识作为一个有序的控制规则集，称为政策，并使用遗传编程学习。遗传程序的交叉和变异算子通过一个简单的局部搜索来增强。L2Plan在blocks world和briefcase域上进行了测试。在这两个领域中，L2Plan能够产生解决所有测试问题的策略，并且优于作者编写的手工编码策略。
There are many different approaches to solving planning problems, one of which is the use of domain specific control knowledge to help guide a domain independent search algorithm. This paper presents L2Plan which represents this control knowledge as an ordered set of control rules, called a policy, and learns using genetic programming. The genetic program's crossover and mutation operators are augmented by a simple local search. L2Plan was tested on both the blocks world and briefcase domains. In both domains, L2Plan was able to produce policies that solved all the test problems and which outperformed the hand-coded policies written by the authors.