Learning to Coordinate Efficiently: A Model-based Approach

Details Learning to Coordinate Efficiently: A Model-based Approach Learning to Coordinate Efficiently: A Model-based Approach

2011-06-26

arxiv.org/abs/1106.5258v1

Journal Of Artificial Intelligence Research, Volume 19, pages 11-23, 2003

Computer Science

Artificial Intelligence

Scientific paper

10.1613/jair.1154

In common-interest stochastic games all players receive an identical payoff. Players participating in such games must learn to coordinate with each other in order to receive the highest-possible value. A number of reinforcement learning algorithms have been proposed for this problem, and some have been shown to converge to good solutions in the limit. In this paper we show that using very simple model-based algorithms, much better (i.e., polynomial) convergence rates can be attained. Moreover, our model-based algorithms are guaranteed to converge to the optimal value, unlike many of the existing algorithms.

Affiliated with

Also associated with

No associations

Rating

Learning to Coordinate Efficiently: A Model-based Approach does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Learning to Coordinate Efficiently: A Model-based Approach, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Learning to Coordinate Efficiently: A Model-based Approach will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-637747