Large Sequence Models For Sequential Decision-making

This survey presents a comprehensive overview of recent works that utilize sequence models such as the Transformer to solve sequential decision-making tasks. It discusses the connection between sequential decision-making and sequence modeling, and categorizes them based on the way they utilize the Transformer. These works suggest the potential for constructing a large decision model for general purposes, that is, a large sequence model that can harness a vast number of parameters to perform hundreds or more sequential decision-making tasks. The authors also summarized recent works that convert the reinforcement learning problem into sequential form to leverage sequence models for specific reinforcement learning settings.