arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.11877cs.LGcs.AI
收藏

在学习Q值的同时学习模型:在线同步MBQ的有限时间样本复杂度

Learning the Model While Learning Q: Finite-Time Sample Complexity of Online SyncMBQ

Korea Advanced Institute of Science and Technology (KAIST)(韩国科学技术院(KAIST));Samsung Electronics(三星电子)

Han-Dong Lim, HyeAnn Lee, Donghwan Lee

AI总结:

本文研究了将Q学习与模型基于方法结合时的样本复杂度,提出在在线方式下同时学习模型和Q值,证明了在广泛步长范围内接近最优的样本复杂度结果。

摘要:

强化学习已取得显著进展,特别是模型基于方法的出现。其中,Q学习在无模型设置中证明是一种强大的算法。然而,将Q学习扩展到模型基于框架仍相对未被探索。本文研究了将Q学习与模型基于方法结合时的样本复杂度。所提出的算法在线方式下同时学习模型和Q值。我们证明了在广泛步长范围内接近最优的样本复杂度结果。

英文摘要:

Reinforcement learning has witnessed significant advancements, particularly with the emergence of model-based approaches. Among these, $Q$-learning has proven to be a powerful algorithm in model-free settings. However, the extension of $Q$-learning to a model-based framework remains relatively unexplored. In this paper, we investigate the sample complexity of $Q$-learning when integrated with a model-based approach. The proposed algorihtms learns both the model and Q-value in an online manner. We demonstrate a near-optimal sample complexity result within a broad range of step sizes.

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。

↑