Synthesizing Programmatic Reinforcement Learning Policies with Large Language Model Guided Search

no code implementations • 26 May 2024 • Max Liu, Chan-Hung Yu, Wei-Hsu Lee, Cheng-Wei Hung, Yen-Chun Chen, Shao-Hua Sun

To further optimize the LLM-generated programs, we develop a search algorithm named Scheduled Hill Climbing, designed to efficiently explore the programmatic search space to consistently improve the programs.

LLM Discussion: Enhancing the Creativity of Large Language Models via Discussion Framework and Role-Play

no code implementations • 10 May 2024 • Li-Chun Lu, Shou-Jen Chen, Tsung-Min Pai, Chan-Hung Yu, Hung-Yi Lee, Shao-Hua Sun

Large language models (LLMs) have shown exceptional proficiency in natural language processing but often fall short of generating creative and original responses to open-ended questions.