Multiagent Learning for Ad Hoc Teamwork in the Era of Generative AI (Peter Stone)

Ad hoc teamwork is based on the premise that as autonomous agents become capable of long-term autonomy, they will increasingly need to band together for cooperative activities with previously unfamiliar teammates. In such "ad hoc" team settings, team strategies cannot be developed a priori. Rather, "controlled" agents must learn to cooperate with new "uncontrolled" teammates on the fly. This talk reports on recent developments on expanding ad hoc teamwork to settings with multiple controlled agents, to open-ended learning settings, and to settings in which humans may provide natural language advice to the controlled agents.