INSIGHT: End-to-End Neuro-Symbolic Visual Reinforcement Learning with Language Explanations

no code implementations • 19 Mar 2024 • Lirui Luo, Guoxi Zhang, Hongming Xu, Yaodong Yang, Cong Fang, Qing Li

In this paper, we present a framework that is capable of learning structured states and symbolic policies simultaneously, whose key idea is to overcome the efficiency bottleneck by distilling vision foundation models into a scalable perception module.

Decision Making