Affiliations: [a] Dipartimento di Ingegneria Informatica, Automatica e Gestionale, Sapienza University of Rome, Italy
| [b] Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, The Netherlands
| [c] Amsterdam Center for Law and Economics and Institute for Logic, Language and Computation, University of Amsterdam, The Netherlands
Correspondence:
[*]
Corresponding author: Davide Grossi, Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, The Netherlands. Amsterdam Center for Law and Economics and Institute for Logic, Language and Computation, University of Amsterdam, The Netherlands. E-mail: d.grossi@rug.nl.
Abstract: This paper focuses on the emergence of communication to support cooperation in environments modeled as social deduction games (SDG), that are games where players communicate freely to deduce each others’ hidden intentions. We first state the problem by giving a general formalization of SDG and a possible solution framework based on reinforcement learning. Next, we focus on a specific SDG, known as The Werewolf, and study if and how various forms of communication influence the outcome of the game. Experimental results show that introducing a communication signal greatly increases the winning chances of a class of players. We also study the effect of the signal’s length and range on the overall performance showing a non-linear relationship.
Keywords: Multi-agent systems, social deduction games, deep reinforcement learning, emergent communication
