New Directions in Cooperative AI

Cooperation is a crucial organizing principle across all scales, from cells to societies. The question, however, of how collective, cooperative behavior emerges from interacting, self-regarding individuals and feeds back to influence those individuals remains open. Complex systems theory focuses on how cooperation emerges from deliberately simple individuals. Fields such as machine learning and cognitive science emphasize individual capabilities in changing environments without considering the collective level much. To date, however, little work went into modeling emergent collective, cooperative behavior from individually self-learning agents. As a result, cooperative intelligence misses out on a holistic complex systems approach, yet-to-be-discovered basic principles on collective cooperative AI cannot find their way into advanced AI systems, and multiagent (human-) machine learning applications may lose out on fulfilling their full cooperative potential. I am proposing a research agenda on collective cooperative AI that will unify classic approaches of multiagent learning, such as reinforcement learning and multi-agent systems, with complex systems theory, i.e., non-linear dynamics and evolutionary game theory.
Speakers

Wolfram Barfuss (University of Tübingen, Princeton University)

Discussants

Jessica Flack (Santa Fe Institute)

Tom Lenaerts (Université Libre de Bruxelles, Umeå University)

Time

15:00-16:30 UTC 19 May 2022

Links

Google calendar event

ICS file

Zoom meeting (passcode sent via mailing list)

Wolfram Barfuss is a research scientist at the Tübingen AI Center at the University of Tübingen in Germany and a guest researcher at the Potsdam Institute for Climate Impact Research and at Princeton University. He studied physics (M.Sc. 2015), with a focus on complex systems at the University of Erlangen-Nuremberg and University College London. In 2019, he received a doctorate in natural science from the Humboldt University Berlin for his work on learning dynamics and decision paradigms in social-ecological dilemmas. During his doctoral work held at the Potsdam Institute for Climate Impact Research, he was also a visiting scholar at the Stockholm Resilience Centre. Before joining the University of Tübingen, he was a research fellow in the School of Mathematics at the University of Leeds and the Max Planck Institute for Mathematics in the Sciences in Leipzig.

Collective Cooperative Intelligence