AIMAJul 23, 2019

E-HBA: Using Action Policies for Expert Advice and Agent Typification

arXiv:1907.09810v19 citations
Originality Incremental advance
AI Analysis

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes