arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.07246cs.LG
收藏

迈向广义逆强化学习

Towards Generalized Inverse Reinforcement Learning

University of Pittsburgh(匹兹堡大学);Amazon(亚马逊公司)

Chaosheng Dong, Yijia Wang

AI总结:

本文研究了马尔可夫决策过程中可能非最优观测下的广义逆强化学习问题,通过量化策略差异并数学刻画不可观测组件,提出了相应的数学公式化与快速启发式算法,在有限和无限状态问题上验证了其有效性。

摘要:

本文研究了马尔可夫决策过程(MDPs)中的广义逆强化学习(GIRL)问题,即在给定可能非最优的观测行为(策略)下学习MDP基本组件的问题。这些组件不仅包括奖励函数和转移概率矩阵,还包括不完全已知但已知属于给定不确定性集合的动作空间和状态空间。我们解决了GIRL中的两个关键挑战:首先,需要量化观测策略与潜在最优策略之间的差异;其次,当MDP的基本组件不可观测或部分可观测时,难以对潜在最优策略进行数学刻画。随后,我们提出了GIRL的数学公式化,并开发了一种快速启发式算法。在有限和无限状态问题上的数值结果证明了我们公式化和算法的优势。

英文摘要:

This paper studies generalized inverse reinforcement learning (GIRL) in Markov decision processes (MDPs), that is, the problem of learning the basic components of an MDP given observed behavior (policy) that might not be optimal. These components include not only the reward function and transition probability matrices, but also the action space and state space that are not exactly known but are known to belong to given uncertainty sets. We address two key challenges in GIRL: first, the need to quantify the discrepancy between the observed policy and the underlying optimal policy; second, the difficulty of mathematically characterizing the underlying optimal policy when the basic components of an MDP are unobservable or partially observable. Then, we propose the mathematical formulation for GIRL and develop a fast heuristic algorithm. Numerical results on both finite and infinite state problems show the merit of our formulation and algorithm.

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。

↑