自己学習型ほぼリアプノフ批評家によるニューラル制御の安定化
Stabilizing Neural Control Using Self-Learned Almost Lyapunov Critics
モデルフリー強化学習でニューラル制御方策とリアプノフ批評家関数を同時に学習し、ほぼリアプノフ条件で吸引領域と不変性を推定して非線形システムの制御安定性を高める手法を提案した。
著者: Ya-Chien Chang, Sicun Gao
分類: cs.RO, cs.SY, eess.SY
原文アブストラクト
The lack of stability guarantee restricts the practical use of learning-based methods in core control problems in robotics. We develop new methods for learning neural control policies and neural Lyapunov critic functions in the model-free reinforcement learning (RL) setting. We use sample-based approaches and the Almost Lyapunov function conditions to estimate the region of attraction and invariance properties through the learned Lyapunov critic functions. The methods enhance stability of neural controllers for various nonlinear systems including automobile and quadrotor control.
