arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2402.02700cs.LGstat.ML
收藏

线性上下文马尔可夫决策过程的样本复杂度刻画

Sample Complexity Characterization for Linear Contextual MDPs

The Ohio State University(俄亥俄州立大学);National University of Singapore(新加坡国立大学);University at Buffalo(纽约州立大学布法罗分校)

Junze Deng, Yuan Cheng, Shaofeng Zou, Yingbin Liang

AI总结:

本文刻画了线性上下文马尔可夫决策过程的样本复杂度,提出了两种模型下的基于模型算法,分别达到多项式样本复杂度,并表明上下文变化特征优于共享表示。

摘要:

上下文马尔可夫决策过程(CMDPs)描述了一类强化学习问题,其中转移核和奖励函数可以随时间变化,不同的MDP由上下文变量索引。虽然CMDPs作为建模许多具有时变环境的实际应用的重要框架,但从理论角度来看,它们在很大程度上未被探索。在本文中,我们在两种线性函数逼近模型下研究CMDPs:模型I具有上下文变化的表示和所有上下文共享的线性权重;模型II具有所有上下文共享的表示和上下文变化的线性权重。对于这两种模型,我们提出了新颖的基于模型的算法,并证明它们享有保证的ε-次优性差距,具有理想的多项式样本复杂度。特别地,将我们针对第一个模型的结果实例化到表格CMDP中,通过移除可达性假设改进了现有结果。我们针对第二个模型的结果是此类函数逼近模型的第一个已知结果。我们两种模型结果的比较进一步表明,在线性CMDP下,具有上下文变化的特征比所有上下文共享表示能带来更好的样本效率。

英文摘要:

Contextual Markov decision processes (CMDPs) describe a class of reinforcement learning problems in which the transition kernels and reward functions can change over time with different MDPs indexed by a context variable. While CMDPs serve as an important framework to model many real-world applications with time-varying environments, they are largely unexplored from theoretical perspective. In this paper, we study CMDPs under two linear function approximation models: Model I with context-varying representations and common linear weights for all contexts; and Model II with common representations for all contexts and context-varying linear weights. For both models, we propose novel model-based algorithms and show that they enjoy guaranteed $ε$-suboptimality gap with desired polynomial sample complexity. In particular, instantiating our result for the first model to the tabular CMDP improves the existing result by removing the reachability assumption. Our result for the second model is the first-known result for such a type of function approximation models. Comparison between our results for the two models further indicates that having context-varying features leads to much better sample efficiency than having common representations for all contexts under linear CMDPs.

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。

↑