• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Intelligent Agent Technology, IEEE/WIC/ACM International Conference on >Decomposing large-scale POMDP via belief state analysis
【24h】

Decomposing large-scale POMDP via belief state analysis

机译：通过信念状态分析分解大规模POMDP

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Partially observable Markov decision process (POMDP) is commonly used to model a stochastic environment with unobservable states for supporting optimal decision making. Computing the optimal policy for a large-scale POMDP is known to be intractable. Belief compression, being an approximate solution, has recently been proposed to reduce the dimension of POMDP's belief state space and shown to be effective in improving the problem tractability. In this paper, with the conjecture that temporally close belief states could be characterized by a lower intrinsic dimension, we propose a spatio-temporal brief clustering that considers both the belief states' spatial (in the belief space) and temporal similarities, as well as incorporate it into the belief compression algorithm. The proposed clustering results in belief state clusters as sub-POMDPs of much lower dimension so as to be distributed to a set of distributed agents for collaborative problem solving. The proposed method has been tested using a synthesized navigation problem (Hallway2) and empirically shown to be able to result in policies of superior long-term rewards when compared with those based on solely belief compression. Some future research directions for extending this belief state analysis approach are also included.
机译：部分可观察的马尔可夫决策过程（POMDP）通常用于对具有不可观察状态的随机环境进行建模，以支持最佳决策。众所周知，为大型POMDP计算最佳策略是很棘手的。信念压缩是一种近似的解决方案，最近已被提出来减小POMDP信念状态空间的维数，并被证明可以有效地提高问题的可处理性。在本文中，我们推测时间上接近的信念状态可以通过较低的内在维数来表征，我们提出了时空简短聚类，该聚类考虑了信念状态的空间（在信念空间中）和时间上的相似性，以及将其合并到置信度压缩算法中。所提出的聚类导致信念状态聚类为维度较低的子POMDP，以便分发给一组分布式代理以解决协作问题。所提出的方法已使用综合导航问题（Hallway2）进行了测试，并通过实验证明，与仅基于信念压缩的策略相比，该策略能够带来更高的长期回报策略。还包括一些扩展该信念状态分析方法的未来研究方向。

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