AI RESEARCH
When to ASK: Uncertainty-Gated Language Assistance for Reinforcement Learning
arXiv CS.LG
•
ArXi:2604.02226v1 Announce Type: cross Reinforcement learning (RL) agents often struggle with out-of-distribution (OOD) scenarios, leading to high uncertainty and random behavior. While language models (LMs) contain valuable world knowledge, larger ones incur high computational costs, hindering real-time use, and exhibit limitations in autonomous planning. We