A POMDP Approach to Influence Diagram Evaluation

A POMDP Approach to Influence Diagram Evaluation
复制标题

影响图评估的 POMDP 方法

DOI:
--
复制
发表时间:
2016
期刊:
International Joint Conference on Artificial Intelligence
影响因子:
--
通讯作者:
Arindam Khaled
Arindam Khaled
中科院分区:
--
文献类型:
--
作者:
E. Hansen;Jinchuan Shi;Arindam Khaled

文献摘要

被引文献

相似文献

我们提出了一种用于影响图评估的节点移除/弧反转算法,该算法包括允许通过求解部分可观察马尔可夫决策过程(pomdp)的动态规划方法的泛化来求解影响图的约简。在其潜在优势中,该算法允许更灵活的节点删除排序,并采用pomdp启发的方法对隐藏状态变量进行优化,这可以提高影响图评估在解决复杂多阶段问题时的可扩展性。它还找到了最优策略的更紧凑的表示。
We propose a node-removal/arc-reversal algorithm for influence diagram evaluation that includes reductions that allow an influence diagram to be solved by a generalization of the dynamic programming approach to solving partially observable Markov decision processes (POMDPs). Among its potential advantages, the algorithm allows a more flexible ordering of node removals, and a POMDP-inspired approach to optimizing over hidden state variables, which can improve the scalability of influence diagram evaluation in solving complex, multi-stage problems. It also finds a more compact representation of an optimal strategy.