• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>PRICAI'98 : Topics in artificial intelligence >Dynamic Non-uniform Abstractions for Approximate Planning in Large Structured Stochastic Domains
【24h】

Dynamic Non-uniform Abstractions for Approximate Planning in Large Structured Stochastic Domains

机译：大结构随机域中近似规划的动态非均匀抽象

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

The theory of Markov Decision Processes (MDPs) provides algorithms for generating an optimal policy. For large domains these algorithms become intractable and approximate solutions become necessary. In this paper we extend previous work on approximate planning in large stochastic domains by using automatically-generated non-uniform abstractions which exploit the structure of the state space. We consider a state space expressed as a cross product of sets, or dimensions. We obtain approximate solutions by varying the level of abstraction, selectively ignoring some of the dimensions in some parts of the state space. We describe a modification of a standard policy generation algorithm for the now non-Markovian decision process, which re-calculates values for nearby states based on a locally uniform abstraction for each state. We present methods to automatically generate an initial abstraction based on the domain structure and to automatically modify the non-uniform abstraction. The changes to the abstraction are based on both the current policy and the likelihood of encountering particular states in the future, thereby taking into account the agent's changing circumstances.
机译：马尔可夫决策过程（MDP）理论提供了用于生成最佳策略的算法。对于大型域，这些算法变得棘手，并且需要近似解决方案。在本文中，我们使用自动生成的利用状态空间结构的非均匀抽象，扩展了先前在大型随机域中进行近似规划的工作。我们考虑状态空间，表示为集合或维度的叉积。我们通过改变抽象级别来获得近似解决方案，有选择地忽略状态空间某些部分中的某些维。我们为现在的非马尔可夫决策过程描述了标准策略生成算法的修改，该算法基于每个状态的局部统一抽象重新计算附近状态的值。我们提出了基于域结构自动生成初始抽象并自动修改非均匀抽象的方法。对抽象的更改基于当前策略以及将来遇到特定状态的可能性，因此要考虑代理的变化情况。

著录项

  • 来源
  • 会议地点 Singapore(SG);Singapore(SG)
  • 作者

    J. Baum; A.E. Nicholson;

  • 作者单位

    School of Computer Science and Software Engineering Monash University, Clayton, Victoria 3168, Australia;

    School of Computer Science and Software Engineering Monash University, Clayton, Victoria 3168, Australia;

  • 会议组织
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类 自动化系统理论;
  • 关键词

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