Efficient Structure Learning in Factored-State MDPs
Efficient Structure Learning in Factored-State MDPs
复制标题
因子状态 MDP 中的高效结构学习
DOI：
--
复制
发表时间：
2007
期刊：
影响因子：
--
通讯作者：
M. Littman
中科院分区：
文献类型：
--
作者：
Alexander L. Strehl;Carlos Diuk;M. Littman
我们考虑的问题，强化学习的factored-state MDPs的设置中，学习是在一个长期的试验，不允许重置。我们展示了如何扩展现有的高效算法，学习动态贝叶斯网络（DBN）的条件概率表，其结构的情况下，DBN结构是事先不知道的。我们的方法学习的DBN结构的学习过程的一部分，并可证明提供了一个有效的学习算法时，与因子Rmax相结合。
We consider the problem of reinforcement learning in factored-state MDPs in the setting in which learning is conducted in one long trial with no resets allowed. We show how to extend existing efficient algorithms that learn the conditional probability tables of dynamic Bayesian networks (DBNs) given their structure to the case in which DBN structure is not known in advance. Our method learns the DBN structures as part of the reinforcement-learning process and provably provides an efficient learning algorithm when combined with factored Rmax.