arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.09875cs.LGcs.AI
收藏

反步时序差分学习

Backstepping Temporal Difference Learning

KAIST(韩国科学技术院)

Han-Dong Lim, Donghwan Lee

AI总结:

针对离策略线性函数近似下时序差分(TD)学习的发散问题,本研究从控制理论视角统一现有算法,并基于反步技术提出新收敛算法,实验验证其在标准TD学习不稳定环境中的收敛性。

摘要:

离策略学习能力是强化学习(RL)在实际应用中的重要特征。然而,即使是最基础的RL算法之一——时序差分(TD)学习,当与线性函数近似结合使用离策略方案时,也存在发散问题。为解决该发散行为,目前已开发出多种离策略TD学习算法,包括梯度TD学习(GTD)和带修正的TD学习(TDC)。本研究从纯控制理论视角对这类算法提供统一视图,并提出一种新的收敛算法。该方法依赖于非线性控制理论中广泛使用的反步技术。最后,在标准TD学习已知不稳定的环境中,通过实验验证了所提算法的收敛性。

英文摘要:

Off-policy learning ability is an important feature of reinforcement learning (RL) for practical applications. However, even one of the most elementary RL algorithms, temporal-difference (TD) learning, is known to suffer form divergence issue when the off-policy scheme is used together with linear function approximation. To overcome the divergent behavior, several off-policy TD-learning algorithms, including gradient-TD learning (GTD), and TD-learning with correction (TDC), have been developed until now. In this work, we provide a unified view of such algorithms from a purely control-theoretic perspective, and propose a new convergent algorithm. Our method relies on the backstepping technique, which is widely used in nonlinear control theory. Finally, convergence of the proposed algorithm is experimentally verified in environments where the standard TD-learning is known to be unstable.

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。

↑