This paper experimentally evaluates multiagent learning algorithms playing repeated matrix games to maximize their cumulative return. Previous works assessed that Qlearning surpas...
We propose a new set of criteria for learning algorithms in multi-agent systems, one that is more stringent and (we argue) better justified than previous proposed criteria. Our cr...
Product Distribution (PD) theory is a new framework for controlling Multi-Agent Systems (MAS’s). First we review one motivation of PD theory, as the information-theoretic extens...
Bayesian inference is an appealing approach for leveraging prior knowledge in reinforcement learning (RL). In this paper we describe an algorithm for discovering different classes...
Although well understood in the single-agent framework, the use of traditional reinforcement learning (RL) algorithms in multi-agent systems (MAS) is not always justified. The fe...