arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1206.3281cs.AI
收藏

大结构域中基于模型的贝叶斯强化学习

Model-Based Bayesian Reinforcement Learning in Large Structured Domains

McGill University(麦吉尔大学);School of Computer Science(计算机学院)

Stephane Ross, Joelle Pineau

摘要:

基于模型的贝叶斯强化学习在人工智能社区中引起了极大的兴趣,因为它为经典强化学习中的最佳探索-利用权衡提供了一个优雅的解决方案。不幸的是,这种类型的方法的适用性已被限制到小域,由于推理的联合后验模型参数的高复杂性。在本文中,我们考虑使用因子表示结合在线规划技术,以提高这些方法的可扩展性。本文的主要贡献是学习动态系统的结构和参数的贝叶斯框架,同时也规划一个(近)最优的行动序列。

英文摘要:

Model-based Bayesian reinforcement learning has generated significant interest in the AI community as it provides an elegant solution to the optimal exploration-exploitation tradeoff in classical reinforcement learning. Unfortunately, the applicability of this type of approach has been limited to small domains due to the high complexity of reasoning about the joint posterior over model parameters. In this paper, we consider the use of factored representations combined with online planning techniques, to improve scalability of these methods. The main contribution of this paper is a Bayesian framework for learning the structure and parameters of a dynamical system, while also simultaneously planning a (near-)optimal sequence of actions.

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。

↑