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 2301.00521cs.ROcs.LG
收藏

面向最优时间稳定性的策略优化方法

A Policy Optimization Method Towards Optimal-time Stability

Tsinghua University(清华大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Shanghai Qi Zhi Institute(上海期智研究院);City University of Hong Kong(香港城市大学);Covenant University(科文特大学)

Shengjie Wang, Fengbo Lan, Xiang Zheng, Yuxue Cao, Oluwatosin Oseni, Haotian Xu, Tao Zhang, Yang Gao

AI总结:

本文提出一种结合采样李雅普诺夫稳定性的策略优化方法,使系统在最优时间内达到稳定,并基于Actor-Critic框架开发ALAC算法,在十个机器人任务上显著优于现有方法。

摘要:

在当前的基于模型无关的强化学习(RL)算法中,基于采样方法的稳定性准则通常被用于指导策略优化。然而,这些准则仅保证系统状态在无限时间内收敛到平衡点,这导致了策略的次优性。在本文中,我们提出了一种结合基于采样的李雅普诺夫稳定性的策略优化技术。我们的方法使系统状态能够在最优时间内达到平衡点,并在之后保持稳定性,称为“最优时间稳定性”。为了实现这一目标,我们将优化方法集成到Actor-Critic框架中,从而开发了自适应李雅普诺夫Actor-Critic(ALAC)算法。通过在十个机器人任务上的评估,我们的方法显著优于以往的研究,有效引导系统生成稳定的模式。

英文摘要:

In current model-free reinforcement learning (RL) algorithms, stability criteria based on sampling methods are commonly utilized to guide policy optimization. However, these criteria only guarantee the infinite-time convergence of the system's state to an equilibrium point, which leads to sub-optimality of the policy. In this paper, we propose a policy optimization technique incorporating sampling-based Lyapunov stability. Our approach enables the system's state to reach an equilibrium point within an optimal time and maintain stability thereafter, referred to as "optimal-time stability". To achieve this, we integrate the optimization method into the Actor-Critic framework, resulting in the development of the Adaptive Lyapunov-based Actor-Critic (ALAC) algorithm. Through evaluations conducted on ten robotic tasks, our approach outperforms previous studies significantly, effectively guiding the system to generate stable patterns.

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。

↑