Multiagent learning using a variable learning rate
Artificial Intelligence
Performance bounded reinforcement learning in strategic interactions
AAAI'04 Proceedings of the 19th national conference on Artifical intelligence
Proceedings of the 7th international joint conference on Autonomous agents and multiagent systems - Volume 1
Using adaptive consultation of experts to improve convergence rates in multiagent learning
Proceedings of the 7th international joint conference on Autonomous agents and multiagent systems - Volume 3
Online Multiagent Learning against Memory Bounded Adversaries
ECML PKDD '08 Proceedings of the 2008 European Conference on Machine Learning and Knowledge Discovery in Databases - Part I
Approximation guarantees for fictitious play
Allerton'09 Proceedings of the 47th annual Allerton conference on Communication, control, and computing
Hi-index | 0.00 |
We present a new multiagent learning algorithm (RVσ(t) that can guarantee both no-regret performance (all games) and policy convergence (some games of arbitrary size). Unlike its predecessor ReDVaLeR, it (1) does not need to distinguish whether its opponents are self-play or otherwise non-stationary, (2) is allowed to know its portion of any equilibrium that, we argue, leads to convergence in some games in addition to no-regret. Although the regret of RVσ(t) is analyzed in continuous time, we show that it grows slower than in other no-regret techniques like GIGA and GIGA-WoLF. We show that RVσ(t) can converge to coordinated behavior in coordination games, while GIGA, GIGA-WoLF may converge to poorly coordinated (mixed) behaviors.