E-HBA: Using Action Policies for Expert Advice and Agent Typification
This work addresses performance improvement for expert algorithms in game theory, but it appears incremental as it builds on existing methods without a paradigm shift.
The paper tackles the problem of improving expert algorithms in repeated interactions by combining expert advice and agent typification into a meta-algorithm called E-HBA, which mixes past payoffs with predicted future payoffs. The results show that E-HBA significantly enhances performance in repeated matrix games.
Past research has studied two approaches to utilise predefined policy sets in repeated interactions: as experts, to dictate our own actions, and as types, to characterise the behaviour of other agents. In this work, we bring these complementary views together in the form of a novel meta-algorithm, called Expert-HBA (E-HBA), which can be applied to any expert algorithm that considers the average (or total) payoff an expert has yielded in the past. E-HBA gradually mixes the past payoff with a predicted future payoff, which is computed using the type-based characterisation. We present results from a comprehensive set of repeated matrix games, comparing the performance of several well-known expert algorithms with and without the aid of E-HBA. Our results show that E-HBA has the potential to significantly improve the performance of expert algorithms.