Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

13

ICML
2000
IEEE

favoriteEmaildiscussreport

192views Machine Learning» more ICML 2000»

Convergence Problems of General-Sum Multiagent Reinforcement Learning

14 years 5 months ago

Convergence Problems of General-Sum Multiagent Reinforcement Learning

Download www.cs.ualberta.ca

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 multiagent Q-learning method for general-sum stochastic games. In addition to describing the algorithm, they provide a proof that the method will converge to a Nash equilibrium for the game under specified conditions. The convergence depends on a lemma stating that the iteration used by this method is a contraction mapping. Unfortunately the proof is incomplete. In this paper we present a counterexample and flaw to the lemma's proof. We also introduce strengthened assumptions under which the lemma holds, and examine how this affects the classes of games to which the theoretical result can be applied.

Michael H. Bowling

Real-time Traffic

General-sum Stochastic Games | ICML 2000 | Machine Learning | Multiagent Q-learning Method | Stochastic Games |

claim paper

Related Content

» Multiagent Relational Reinforcement Learning

» The Dynamics of MultiAgent Reinforcement Learning

» Multiagent learning using a variable learning rate

» Theoretical advantages of lenient Qlearners an evolutionary game theoretic perspective

» A Multiagent Reinforcement Learning Algorithm with Nonlinear Dynamics

» Coordination in multiagent reinforcement learning a Bayesian approach

» Rational and Convergent Learning in Stochastic Games

» Multiagent reinforcement learning algorithm converging to Nash equilibrium in generalsum d...

» TimeExtended Policies in MultiAgent Reinforcement Learning

Post Info
More Details (n/a)

Added	17 Nov 2009
Updated	17 Nov 2009
Type	Conference
Year	2000
Where	ICML
Authors	Michael H. Bowling

Comments (0)