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 …
J Suriadinata, W Macke, R Mirsky, P Stone - Adaptive and learning …, 2021 - par.nsf.gov
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 …