Sciweavers

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

11

ICML
1998
IEEE

favoriteEmaildiscussreport

155views Machine Learning» more ICML 1998»

Multiagent Reinforcement Learning: Theoretical Framework and an Algorithm

14 years 5 months ago

Multiagent Reinforcement Learning: Theoretical Framework and an Algorithm

Download www.lirmm.fr

In this paper, we adopt general-sum stochastic games as a framework for multiagent reinforcement learning. Our work extends previous work by Littman on zero-sum stochastic games to a broader framework. We design a multiagent Q-learning method under this framework, and prove that it converges to a Nash equilibrium under speci ed conditions. This algorithm is useful for nding the optimal strategy when there exists a unique Nash equilibrium in the game. When there exist multiple Nash equilibria in the game, this algorithm should be combined with other learning techniques to nd optimal strategies.

Junling Hu, Michael P. Wellman

Real-time Traffic

ICML 1998 | Machine Learning | Multiple Nash Equilibria | Unique Nash Equilibrium | Zero-sum Stochastic Games |

claim paper

Related Content

» Convergence Problems of GeneralSum Multiagent Reinforcement Learning

» Multiagent learning using a variable learning rate

» Theoretical advantages of lenient Qlearners an evolutionary game theoretic perspective

» The Dynamics of MultiAgent Reinforcement Learning

» Markov Games as a Framework for MultiAgent Reinforcement Learning

» BestResponse Multiagent Learning in NonStationary Environments

» Multiagent Learning Dynamics A Survey

» Asymmetric Multiagent Reinforcement Learning

» Analysis of an evolutionary reinforcement learning method in a multiagent domain

Post Info
More Details (n/a)

Added	17 Nov 2009
Updated	17 Nov 2009
Type	Conference
Year	1998
Where	ICML
Authors	Junling Hu, Michael P. Wellman

Comments (0)