作者
Roxana Rădulescu, Timothy Verstraeten, Yijie Zhang, Patrick Mannion, Diederik M Roijers, Ann Nowé
发表日期
2022/2/1
期刊
Neural Computing and Applications
页码范围
1-23
出版商
Springer London
简介
Many real-world multi-agent interactions consider multiple distinct criteria, i.e. the payoffs are multi-objective in nature. However, the same multi-objective payoff vector may lead to different utilities for each participant. Therefore, it is essential for an agent to learn about the behaviour of other agents in the system. In this work, we present the first study of the effects of such opponent modelling on multi-objective multi-agent interactions with nonlinear utilities. Specifically, we consider two-player multi-objective normal form games with nonlinear utility functions under the scalarised expected returns optimisation criterion. We contribute novel actor-critic and policy gradient formulations to allow reinforcement learning of mixed strategies in this setting, along with extensions that incorporate opponent policy reconstruction and learning with opponent learning awareness (i.e. learning while considering the impact of one …
引用总数
20212022202320243961
学术搜索中的文章
R Rădulescu, T Verstraeten, Y Zhang, P Mannion… - Neural Computing and Applications, 2022