63 search results - page 2 / 13 » Convergence and No-Regret in Multiagent Learning |
ICML
2010
IEEE
13 years 9 months ago
2010
IEEE
This paper introduces a novel multiagent learning algorithm, Convergence with Model Learning and Safety (or CMLeS in short), which achieves convergence, targeted optimality agains...
COGSR
2011
13 years 3 months ago
2011
We simulate the evolution of a domain vocabulary in small communities. Empirical data show that human communicators can evolve graphical languages quickly in a constrained task (P...
ATAL
2008
Springer
13 years 10 months ago
2008
Springer
In this paper we study the use of experts algorithms in a multiagent setting. In this paper we allow agents to use multiple experts and explore different experts algorithms that a...
ICML
2000
IEEE
14 years 9 months ago
2000
IEEE
Stochastic games are a generalization of MDPs to multiple agents, and can be used as a framework for investigating multiagent learning. Hu and Wellman (1998) recently proposed a m...
ATAL
2007
Springer
14 years 2 months ago
2007
Springer
Regret based algorithms have been proposed to control a wide variety of multi-agent systems. The appeal of regretbased algorithms is that (1) these algorithms are easily implement...