Language Guided Exploration For RL Agents In Text Environments

Golchha Hitesh, Yerawar Sahil, Patel Dhruvesh, Dan Soham, Murugesan Keerthiram. Arxiv 2024

[Paper]    
Agentic Fine Tuning Model Architecture Pretraining Methods Reinforcement Learning Tools Transformer

Real-world sequential decision making is characterized by sparse rewards and large decision spaces, posing significant difficulty for experiential learning systems like \(\textit{tabula rasa}\) reinforcement learning (RL) agents. Large Language Models (LLMs), with a wealth of world knowledge, can help RL agents learn quickly and adapt to distribution shifts. In this work, we introduce Language Guided Exploration (LGE) framework, which uses a pre-trained language model (called GUIDE ) to provide decision-level guidance to an RL agent (called EXPLORER). We observe that on ScienceWorld (Wang et al.,2022), a challenging text environment, LGE outperforms vanilla RL agents significantly and also outperforms other sophisticated methods like Behaviour Cloning and Text Decision Transformer.

Similar Work