Multi-agents Ultimatum Game with Reinforcement Learning

Tangui Le Gléau (1, 2) , Xavier Marjou (1) , Tayeb Lemlouma (3, 4) , Benoit Radier (1)

1 Orange Labs [Lannion]
2 IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires
3 IRISA-D2 - RÉSEAUX, TÉLÉCOMMUNICATION ET SERVICES
4 OCIF - Objets communicants pour l'Internet du futur

The Ultimatum Game is an experimental economics game in which an agent has to propose a sharing partition of a limited amount of resources to other agents who have to accept it or not. If the offer is rejected per consensus, the process of sharing is abandoned. So all agents have to guess what are the best decisions (offer and vote) to optimise their respective gain. We focus on an iterated multi-agent version of Ultimatum Game also known as the Pirate Game, a riddle in which pirates have to share coins according to specific rules. To solve such game, we employ a multi-agent model. In particular, we design a new kind of Artificial Neural Network model able to output an integer partition of discrete finite resources, trained by a Reinforcement Learning agent to identify an acceptable offer to the voting agents. We take an interest in evaluating the performances against several kinds of voting behaviours. The results are close to theoretical optima for all tested scenarios thus demonstrating the flexibility of our method.

Mots clés: Multi-agents systems; Ultimatum game; Reinforcement Learning; Game theory

Domaines: Réseaux et télécommunications [cs.NI]; Système multi-agents [cs.MA]; Intelligence artificielle [cs.AI]; Informatique et théorie des jeux [cs.GT]

Tangui Le Gléau, Xavier Marjou, Tayeb Lemlouma, Benoit Radier. Multi-agents Ultimatum Game with Reinforcement Learning. Fernando De La Prieta; Philippe Mathieu; Jaime Andrés Rincón Arango; Alia El Bolock; Elena Del Val; Jaume Jordán Prunera; João Carneiro; Rubén Fuentes; Fernando Lopes; Vicente Julian. Highlights in Practical Applications of Agents, Multi-Agent Systems, and Trust-worthiness. The PAAMS Collection, 1233, Springer, pp.267-278, 2020, Communications in Computer and Information Science, 978-3-030-51998-8. ⟨10.1007/978-3-030-51999-5_22⟩. ⟨hal-02967163⟩