This project seeks to model goal-directed behavior in collectives through strategic advances beyond the standard AI conceptual frameworks devoted to individual utility maximization. In particular, they aim to establish a simulation platform based on the mathematical formalization of collective goal-seeking that addresses difficulties with the poor scaling of communication and can systematically explore controlled environments where success for agents is only possible through joint decision-making that may be suboptimal for any individual agent. A key output will be open-source software that a larger investigative community can use these formal tools to explore these and allied questions about agency and goal-directed behavior.
Modeling Agency Formally
Emergent intrinsic motivations in intelligent collectives
Subaward Principal Investigator
Ryan Adams is a machine learning researcher and Professor of Computer Science at Princeton University. Ryan completed his Ph.D. in physics under David MacKay at the University of Cambridge, where he was a Gates Cambridge Scholar and a member of St. John's College. Following his Ph.D. Ryan spent two years as a Junior Research Fellow at the University of Toronto as a part of the Canadian Institute for Advanced Research. From 2011-2016, he was an Assistant Professor at Harvard University in the School of Engineering and Applied Sciences. In 2015, Ryan sold the company he co-founded, Whetlab, to Twitter and he spent three years in industry at Twitter and Google before joining the faculty at Princeton in 2018. Ryan has won paper awards at ICML, UAI, and AISTATS, received the DARPA Young Faculty Award and the Alfred P. Sloan Fellowship. He also co-hosted the popular Talking Machines podcast.