Loftin, R. and Oliehoek, F.A. (2022) On the impossibility of learning to cooperate with adaptive partner strategies in repeated games. In: Proceedings of the 39th International Conference on Machine Learning. 39th International Conference on Machine Learning, 17-23 Jul 2022, Baltimore, MD, USA. Proceedings of Machine Learning Research, 162 . ML Research Press , pp. 14197-14209.
Abstract
Learning to cooperate with other agents is challenging when those agents also possess the ability to adapt to our own behavior. Practical and theoretical approaches to learning in cooperative settings typically assume that other agents' behaviors are stationary, or else make very specific assumptions about other agents' learning processes. The goal of this work is to understand whether we can reliably learn to cooperate with other agents without such restrictive assumptions, which are unlikely to hold in real-world applications. Our main contribution is a set of impossibility results, which show that no learning algorithm can reliably learn to cooperate with all possible adaptive partners in a repeated matrix game, even if that partner is guaranteed to cooperate with some stationary strategy. Motivated by these results, we then discuss potential alternative assumptions which capture the idea that an adaptive partner will only adapt rationally to our behavior.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2022 The Author(s). |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 16 Feb 2024 13:44 |
Last Modified: | 16 Feb 2024 13:44 |
Published Version: | https://proceedings.mlr.press/v162/loftin22a.html |
Status: | Published |
Publisher: | ML Research Press |
Series Name: | Proceedings of Machine Learning Research |
Refereed: | Yes |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:209126 |