Loftin, R., Çelikok, M.M., van Hoof, H. et al. (2 more authors) (2024) Uncoupled learning of differential Stackelberg equilibria with commitments. In: Proceedings of AAMAS-2024. The 23rd International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS 2024), 06-10 May 2024, Auckland, New Zealand. International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS) , pp. 1265-1273. ISBN 978-1-4007-0486-4
Abstract
In multi-agent problems requiring a high degree of cooperation, success often depends on the ability of the agents to adapt to each other’s behavior. A natural solution concept in such settings is the Stackelberg equilibrium, in which the “leader” agent selects the strategy that maximizes its own payoff given that the “follower” agent will choose their best response to this strategy. Recent work has extended this solution concept to two-player differentiable games, such as those arising from multi-agent deep reinforcement learning, in the form of the differential Stackelberg equilibrium. While this previous work has presented learning dynamics which converge to such equilibria, these dynamics are “coupled” in the sense that the learning updates for the leader’s strategy require some information about the follower’s payoff function. As such, these methods cannot be applied to truly decentralised multi-agent settings, particularly ad hoc cooperation, where each agent only has access to its own payoff function. In this work we present “uncoupled” learning dynamics based on zeroth-order gradient estimators, in which each agent’s strategy update depends only on their observations of the other’s behavior. We analyze the convergence of these dynamics in general-sum games, and prove that they converge to differential Stackelberg equilibria under the same conditions as previous coupled methods. Furthermore, we present an online mechanism by which symmetric learners can negotiate leader-follower roles. We conclude with a discussion of the implications of our work for multi-agent reinforcement learning and ad hoc collaboration more generally.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2024 International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS). This work is licensed under a Creative Commons Attribution International 4.0 License (https://creativecommons.org/licenses/by/4.0/). |
Keywords: | multi-agent reinforcement learning; ad hoc collaboration; ad hoc teamwork; learning dynamics; differentiable games; differential stackelberg equilibrium |
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: | 14 Feb 2024 15:24 |
Last Modified: | 22 May 2024 08:19 |
Published Version: | https://www.ifaamas.org/Proceedings/aamas2024/form... |
Status: | Published |
Publisher: | International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS) |
Refereed: | Yes |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:209131 |