Learning to Participate Through Trading of Reward Share

Kölle, Michael; Matheis, Tim; Altmann, Philipp und Schmid, Kyrill (2023): Learning to Participate Through Trading of Reward Share. ICAART 2023 : International Conference on Agents and Artificial Intelligence, Lissabon, Portugal, 22. - 24. Februar 2023. Rocha, Ana Paula; Steels, Luc und Herik, Jaap van den (eds.) : In: Proceedings of the 15th International Conference on Agents and Artificial Intelligence, Vol. 1 Setúbal: SciTePress. pp. 355-362

Abstract

Enabling autonomous agents to act cooperatively is an important step to integrate artificial intelligence in our daily lives. While some methods seek to stimulate cooperation by letting agents give rewards to others, in this paper we propose a method inspired by the stock market, where agents have the opportunity to participate in other agents’ returns by acquiring reward shares. Intuitively, an agent may learn to act according to the common interest when being directly affected by the other agents’ rewards. The empirical results of the tested general-sum Markov games show that this mechanism promotes cooperative policies among independently trained agents in social dilemma situations. Moreover, as demonstrated in a temporally and spatially extended domain, participation can lead to the development of roles and the division of subtasks between the agents.

• Item Type: Conference or Workshop Item (Paper)
• Keywords: Multi-Agent Systems, Reinforcement Learning, Social Dilemma
• Faculties: Mathematics, Computer Science and Statistics; Mathematics, Computer Science and Statistics > Computer Science
• Subjects: 000 Computer science, information and general works > 004 Data processing computer science
• ISBN: 978-989-758-623-1
• Place of Publication: Setúbal
• Language: English