Learning to Participate Through Trading of Reward Shares

Michael Kölle, Tim Matheis, Philipp Altmann, Kyrill Schmid

2023

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.

Paper Citation

in Harvard Style

Kölle M., Matheis T., Altmann P. and Schmid K. (2023). Learning to Participate Through Trading of Reward Shares. In Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART, ISBN 978-989-758-623-1, pages 355-362. DOI: 10.5220/0011781600003393

in Bibtex Style

@conference{icaart23,
author={Michael Kölle and Tim Matheis and Philipp Altmann and Kyrill Schmid},
title={Learning to Participate Through Trading of Reward Shares},
booktitle={Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,},
year={2023},
pages={355-362},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011781600003393},
isbn={978-989-758-623-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,
TI - Learning to Participate Through Trading of Reward Shares
SN - 978-989-758-623-1
AU - Kölle M.
AU - Matheis T.
AU - Altmann P.
AU - Schmid K.
PY - 2023
SP - 355
EP - 362
DO - 10.5220/0011781600003393