首页> 外文会议>International Conference on Automated Planning and Scheduling(ICAPS 2006); 2006; >Goal Achievement in Partially Known, Partially Observable Domains
【24h】

Goal Achievement in Partially Known, Partially Observable Domains

机译:部分已知,部分可观察的领域中的目标成就

获取原文
获取原文并翻译 | 示例

摘要

We present a decision making algorithm for agents that act in partially observable domains which they do not know fully. Making intelligent choices in such domains is very difficult because actions' effects may not be known a priori (partially known domain), and features may not always be visible (partially observable domain). Nonetheless, we show that an efficient solution is achievable in STRIPS domains by using traditional planning methods. This solution interleaves planning and execution carefully. Computing each plan takes time that is linear in the planning time for the fully observable, fully known domain. The number of actions that it executes is bounded by a polynomial in the length of the optimal plan in the fully observable, fully known domain. Our theoretical results and preliminary experiments demonstrate the effectiveness of the algorithm.
机译:我们为在不完全了解的部分可观察域中起作用的代理提供了一种决策算法。在这样的领域中做出明智的选择非常困难,因为行动的影响可能不是先验的(部分已知的领域),并且功能可能并不总是可见的(部分可观察的领域)。尽管如此,我们表明使用传统的规划方法在STRIPS领域中可以实现有效的解决方案。该解决方案仔细地规划和执行。计算每个计划所花费的时间与完全可观察,众所周知的领域的计划时间成线性关系。在完全可观察的,众所周知的域中,它执行的操作数受最佳计划长度的多项式的限制。我们的理论结果和初步实验证明了该算法的有效性。

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