The computation of agreements – or conventions- in agents’ societies via social learning methods, when agents aim to perform tasks in coordination with others is a challenge, especially when agents have to achieve multiple and conflicting goals simultaneously w.r.t. operational constraints, jointly with their peers, in settings with limited monitoring and interaction abilities.

In this line of research we investigate the use of multi-agent reinforcement learning methods to advance agents’ ability to act jointly, aiming to reaching equilibria or optima regarding their payoffs.