Foundation Models for Decision Making

We invite submissions in the area of foundation models and decision making on topics such as, but not limited to:

• Foundation model agents interacting with humans, computers, tools, simulators, physical world, and each other.

• Rethinking the implementation, ecosystem, and model modularity of decision making agents under emerging technologies such as ChatGPT and language model plug-ins.

• Applying foundation models to traditional decision making problems in control, planning, online / offline RL.

• Learning multi-modal, multi-task, multi-environment, and generalist policies.

• Long-horizon reasoning and planning in language models.

• New evaluation protocols, benchmarks, datasets, and applications that apply foundation models to solve decision making problems.

• Theoretical understanding of the roles foundation models play in decision making.

Please visit the front page for a more detailed summary of what we are excited about. We welcome both theoretical and empirical contributions. Submissions can range from 4 - 10 pages in NeurIPS or ICLR format, where shorter submissions with proof-of-concept demonstrations with live demos, code, and blog posts are welcome.