28 search results - page 1 / 6 » Multi-agent Learning Experiments on Repeated Matrix Games |
ICML
2010
IEEE
13 years 5 months ago
2010
IEEE
This paper experimentally evaluates multiagent learning algorithms playing repeated matrix games to maximize their cumulative return. Previous works assessed that Qlearning surpas...
NIPS
2004
13 years 6 months ago
2004
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...
ATAL
2004
Springer
13 years 10 months ago
2004
Springer
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...
AAAI
2010
13 years 5 months ago
2010
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...
ATAL
2003
Springer
13 years 10 months ago
2003
Springer
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...