he Representational Capacity of Action-Value Networks for Multi-Agent Reinforcement Learning

10^th April 2019, 13:00
Jacopo Castellini
University of Liverpool

Abstract

Recent years have seen the application of deep reinforcement learning techniques to cooperative multi-agent systems, with great empirical success. In this work, we empirically investigate the representational power of various network architectures on a series of one-shot games. Despite their simplicity, these games capture many of the crucial problems that arise in the multi-agent setting, such as an exponential number of joint actions or the lack of an explicit coordination mechanism. Our results quantify how well various approaches can represent the requisite value functions, and help us identify issues that can impede good performance.

Joint work with Frans A. Oliehoek (Delft University of Technology), Rahul Savani (University of Liverpool), Shimon Whiteson (University of Oxford).

To appear as an Extended Abstract in AAMAS '19.