Whether in groups of humans or groups of computer agents, collaboration is most effective
between individuals who have the ability to coordinate on a joint strategy for collective …

While we would like agents that can coordinate with humans, current algorithms such as self-
play and population-based training create agents that can coordinate with themselves …

Ad hoc teamwork is a decentralized multi-agent problem in which agents must collaborate
online without pre-coordination. An interesting challenge in ad hoc teammate design is …

The ad hoc coordination problem is to design an autonomous agent which is able to achieve
optimal flexibility and efficiency in a multiagent system with no mechanisms for prior …

When performing collaborative tasks with new unknown teammates, humans are particularly
adept at adapting to their collaborator and converging toward an aligned strategy. However …

This thesis is concerned with the ad hoc coordination problem, in which the goal is to design
an autonomous agent which is able to achieve optimal flexibility and efficiency in a …

We describe a decision-theoretic method that an autonomous agent can use to model
multiagent situations and behave rationally based on its model. Our approach, which we call …

Conventions are crucial for strong performance in cooperative multi-agent games, because
they allow players to coordinate on a shared strategy without explicit communication …

We adopt the decision-theoretic principle of expected utility maximization as a paradigm for
designing autonomous rational agents, and present a framework that uses this paradigm to …

We adopt the decision-theoretic principle of expected utility maximization as a paradigm for
designing autonomous rational agents, and present a method of representing and …