Workshop: Foundation Models for Decision Making

Decision Making as Language Generation

Roland Memisevic · Sunny P Panchal · Mingu Lee


Decision transformers are a recently proposed approach to offline reinforcement learning that leverages transformer-based auto-regressive sequence models. We discuss challenges associated with fine-tuning a given, pre-trained language model on a decision making task. We propose solutions to these challenges and study their viability on a shortest path problem. We also show how given language model allows us to bring to bear data-centric approaches to improving the model and how it opens up the possibility to treat the decision transformer objective as one task alongside others to perform transfer learning.

Chat is not available.