A Bird's-Eye View of Iterative Reward Design
Designing effective reward functions in RL typically requires substantial expertise and trial and error. Recent work automates this process with LLM-based systems that generate and iteratively improve reward code using policy feedback. However, these methods are often hard to compare because they differ in implementati...
L. M. Bhamidipaty, Lauren Robson, Linda Petrini et al.
· 0 citations