Paper ID: 2312.08958

LiFT: Unsupervised Reinforcement Learning with Foundation Models as Teachers

Taewook Nam, Juyong Lee, Jesse Zhang, Sung Ju Hwang, Joseph J. Lim, Karl Pertsch

We propose a framework that leverages foundation models as teachers, guiding a reinforcement learning agent to acquire semantically meaningful behavior without human feedback. 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 multi-task language-conditioned policy by providing reward feedback. We demonstrate that our method can learn semantically meaningful skills in a challenging open-ended MineDojo environment while prior unsupervised skill discovery methods struggle. Additionally, we discuss observed challenges of using off-the-shelf foundation models as teachers and our efforts to address them.

Submitted: Dec 14, 2023