arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1301.2308cs.AI
收藏

一类排序问题的易处理的POMDP

A Tractable POMDP for a Class of Sequencing Problems

Stanford University(斯坦福大学)

Paat Rusmevichientong, Benjamin van Roy

摘要:

我们考虑一个部分可观察马尔可夫决策问题(POMDP)模型的一类排序问题。虽然POMDPs通常是棘手的,我们的配方承认听话的解决方案。我们将状态空间降维到一个更小的维度,而不是在一个高维的信念状态集合上保持一个价值函数,其中基于网格的动态规划技术是有效的。我们开发了一个误差界的近似结果,并讨论了应用模型的问题,有针对性的广告。

英文摘要:

We consider a partially observable Markov decision problem (POMDP) that models a class of sequencing problems. Although POMDPs are typically intractable, our formulation admits tractable solution. Instead of maintaining a value function over a high-dimensional set of belief states, we reduce the state space to one of smaller dimension, in which grid-based dynamic programming techniques are effective. We develop an error bound for the resulting approximation, and discuss an application of the model to a problem in targeted advertising.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑