LiFT: Unsupervised Reinforcement Learning with Foundation Models as Teachers

Abstract

We propose a framework that leverages foundation models as teachers, guiding a reinforcement learning agent to acquire semantically meaningful behavior without human intervention. In our framework, the agent receives task instructions grounded in a training environment from large language models. Then, a vision-language model guides the agent in learning the tasks by providing reward feedback. We demonstrate that our method can learn semantically meaningful skills in a challenging open-ended MineDojo environment, while prior works on unsupervised skill discovery methods struggle. Additionally, we discuss the observed challenges of using off-the-shelf foundation models as teachers and our efforts to address them.