Publication Details
Overview
 
 
Yijie Zhang, Roxana Radulescu, Patrick Mannion, Diederik Roijers, Ann Nowe
 

Chapter in Book/ Report/ Conference proceeding

Abstract 

In this paper, we investigate the effects of opponent modelling on multi-objective multi-agent interactions with non-linear utilities. Specifically, we consider multi-objective normal form games (MONFGs) with non-linear utility functions under the scalarised expected returns optimisation criterion. We contribute a novel actor-critic formulation to allow reinforcement learning of mixed strategies in this setting, along with an extension that incorporates opponent policy reconstruction using conditional action frequencies. Our empirical results demonstrate that opponent modelling can drastically alter the learning dynamics in this setting.

Reference 
 
 
Link  scopus