QL2, a simple reinforcement learning scheme for two-player zero-sum Markov games: Proceedings of the 16th European Symposium on Artificial Neural Networks

Benoît Frénay, Marco Saerens

Research output: Contribution in Book/Catalog/Report/Conference proceedingConference contribution

Abstract

Markov games is a framework which can be used to formalise n-agent reinforcement learning (RL). Littman (Markov games as a framework for multi-agent reinforcement learning, in: Proceedings of the 11th International Conference on Machine Learning (ICML-94), 1994.) uses this framework to model two-agent zero-sum problems and, within this context, proposes the minimax-Q algorithm. This paper reviews RL algorithms for two-player zero-sum Markov games and introduces a new, simple, fast. algorithm, called 2L(2).2L(2) is compared to several standard algorithms (Q-learning, Minimax and minimax-Q) implemented with the)ash library written in Python. The experiments show that 222 converges empirically to optimal mixed policies, as minimax-Q, but uses a surprisingly simple and cheap updating rule. (C) 2009 Elsevier B.V. All rights reserved.
Original languageEnglish
Title of host publicationProceedings of the 16th European Symposium on Artificial Neural Networks
Pages137-142
Number of pages6
Publication statusPublished - 2009
Externally publishedYes
Event16th European Symposium on Artificial Neural Networks - Advances in Computational Intelligence and Learning, ESANN 2008 - Bruges, Belgium
Duration: 23 Apr 200825 Apr 2008

Conference

Conference16th European Symposium on Artificial Neural Networks - Advances in Computational Intelligence and Learning, ESANN 2008
Country/TerritoryBelgium
CityBruges
Period23/04/0825/04/08

Keywords

  • Reinforcement Learning Q-learning Markov Games Two-player Zero-sum Games Multi-agent

Fingerprint

Dive into the research topics of 'QL2, a simple reinforcement learning scheme for two-player zero-sum Markov games: Proceedings of the 16th European Symposium on Artificial Neural Networks'. Together they form a unique fingerprint.

Cite this