自己教師あり強化学習によるニューラルリアプノフ関数近似
Neural Lyapunov Function Approximation with Self-Supervised Reinforcement Learning
自己教師あり強化学習とデータ駆動型ワールドモデルを組み合わせ、非線形系のリアプノフ関数を効率的に近似する手法を提案し、ロボットタスクで精度と収束速度の向上を示した。
著者: Luc McCutcheon, Bahman Gharesifard, Saber Fallah
分類: cs.RO, cs.AI, cs.CG, cs.LG
原文アブストラクト
Control Lyapunov functions are traditionally used to design a controller which ensures convergence to a desired state, yet deriving these functions for nonlinear systems remains a complex challenge. This paper presents a novel, sample-efficient method for neural approximation of nonlinear Lyapunov functions, leveraging self-supervised Reinforcement Learning (RL) to enhance training data generation, particularly for inaccurately represented regions of the state space. The proposed approach employs a data-driven World Model to train Lyapunov functions from off-policy trajectories. The method is validated on both standard and goal-conditioned robotic tasks, demonstrating faster convergence and higher approximation accuracy compared to the state-of-the-art neural Lyapunov approximation baseline. The code is available at: https://github.com/CAV-Research-Lab/SACLA.git
