Communicating with Unknown Teammates (2014)
Samuel Barrett, Noa Agmon, Noam Hazon, Sarit Kraus, and Peter Stone
Past research has investigated a number of methods for coordinating teams of agents, but with the growing number of sources of agents, it is likely that agents will encounter teammates that do not share their coordination methods. Therefore, it is desirable for agents to adapt to these teammates, forming an effective ad hoc team. Past ad hoc teamwork research has focused on cases where the agents do not directly communicate. However when teammates do communicate, it can provide a valuable channel for coordination. Therefore, this paper tackles the problem of communication in ad hoc teams, introducing a minimal version of the multiagent, multi-armed bandit problem with limited communication between the agents. The theoretical results in this paper prove that this problem setting can be solved in polynomial time when the agent knows the set of possible teammates. Furthermore, the empirical results show that an agent can cooperate with a variety of teammates following unknown behaviors even when its models of these teammates are imperfect.
In Proceedings of the Twenty-First European Conference on Artificial Intelligence, August 2014.

Slides (PDF)
Samuel Barrett Ph.D. Alumni sbarrett [at] cs utexas edu
Peter Stone Faculty pstone [at] cs utexas edu