About this document
Asynchronous Parallel Reinforcement Learning For Optimizing Propulsive Performance in Fin Ray Control by Subhrajit Roy is a document available to read on EtoBox.
This study presents an innovative asynchronous parallel reinforcement learning (APT) algorithm aimed at optimizing fin-ray control for enhanced propulsive performance in fish-like locomotion. By decoupling fluid-structure interaction (FSI) environment interactions from policy optimization, the APT method significantly improves training efficiency compared to conventional deep reinforcement learning approaches. The results demonstrate that the proposed method successfully identifies complex control strategie
- Author
- Subhrajit Roy
- Language
- EN