English

A Policy Optimization Method Towards Optimal-time Stability

Robotics 2023-10-16 v2 Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.2301.00521,
  title  = {A Policy Optimization Method Towards Optimal-time Stability},
  author = {Shengjie Wang and Fengbo Lan and Xiang Zheng and Yuxue Cao and Oluwatosin Oseni and Haotian Xu and Tao Zhang and Yang Gao},
  journal= {arXiv preprint arXiv:2301.00521},
  year   = {2023}
}

Comments

27 pages, 11 figues. 7th Annual Conference on Robot Learning. 2023