arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1602.06346stat.MLcs.LG
收藏

因子化线性模型下基于模型的强化学习策略误差界

Policy Error Bounds for Model-Based Reinforcement Learning with Factored Linear Models

University of Alberta(阿尔伯塔大学)

Bernardo Ávila Pires, Csaba Szepesvári

摘要:

在本文中,我们研究了一个基于模型的方法来计算近似最优的马尔可夫决策过程的政策。特别是,我们得出新的界限上的损失,使用的政策来自一个因子化的线性模型,一类模型,概括了许多以前的模型,那些来与强大的计算保证。在文献中的第一次,我们推导出基于模型的技术,模型的不准确性是衡量加权范数的性能界限。此外,我们的界限显示出降低的敏感性折扣因子,不像其他方法得到的类似的界限,他们是不敏感的测量不匹配。类似于以前的作品,我们的证明也是基于收缩参数,但主要的区别是,我们使用精心构造的规范建设的Banach格,和收缩属性仅假设为运营商作用于“压缩”空间,从而削弱了以前的假设,而加强以前的结果。

英文摘要:

In this paper we study a model-based approach to calculating approximately optimal policies in Markovian Decision Processes. In particular, we derive novel bounds on the loss of using a policy derived from a factored linear model, a class of models which generalize numerous previous models out of those that come with strong computational guarantees. For the first time in the literature, we derive performance bounds for model-based techniques where the model inaccuracy is measured in weighted norms. Moreover, our bounds show a decreased sensitivity to the discount factor and, unlike similar bounds derived for other approaches, they are insensitive to measure mismatch. Similarly to previous works, our proofs are also based on contraction arguments, but with the main differences that we use carefully constructed norms building on Banach lattices, and the contraction property is only assumed for operators acting on "compressed" spaces, thus weakening previous assumptions, while strengthening previous results.

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。

↑