• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Automated Planning and Scheduling(ICAPS 2006); 2006; >Reusing and Building a Policy Library
【24h】

Reusing and Building a Policy Library

机译：重用和构建策略库

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Policy Reuse is a method to improve reinforcement learning with the ability to solve multiple tasks by building upon past problem solving experience, as accumulated in a Policy Library. Given a new task, a Policy Reuse learner uses the past policies in the library as a probabilistic bias in its new learning process. We present how the effectiveness of each reuse episode is indicative of the novelty of the new task with respect to the previously solved ones in the policy library. In the paper we review Policy Reuse, and we introduce theoretical results that demonstrate that: (ⅰ) a Policy Library can be selectively and incrementally built while learning different problems; (ⅱ) the Policy Library can be understood as a basis of the domain that represents its structure through a set of core policies; and (ⅲ) given the basis of a domain, we can define a lower bound for its reuse gain.
机译：策略重用是一种通过基于策略库中积累的过去解决问题的经验来解决问题的能力，从而提高强化学习的方法。给定一项新任务，策略重用学习者将库中的过去策略用作其新学习过程中的概率偏差。我们介绍了每个重用情节的有效性如何指示新任务相对于策略库中以前解决的任务的新颖性。在本文中，我们回顾了策略重用，并介绍了理论结果，这些结果表明：（ⅰ）在学习不同问题的同时可以有选择地逐步建立策略库； （ⅱ）策略库可以理解为通过一组核心策略代表其结构的域的基础； （ⅲ）给定域的基础，我们可以为其重用增益定义一个下限。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号