Image Image Image




Post new topic Reply to topic  [ 1 post ] 
Author Message
 Post subject: Applying Reinforcement Learning to Poker
PostPosted: Sun Aug 12, 2012 2:33 pm 
Offline
Senior member
User avatar

Posts: 124
Favourite Bot: coming
Applying Reinforcement Learning to Poker

Authors : NĂ©ill Sweeney, David Sinclair

Abstract :

This paper describes the application of basic reinforcement learning techniques to the game of multi-player limit hold'em poker.
An approximation to the Nash equilibrium strategy is sought for this large sequential imperfect information game.
A novel connectionist (similar to a neural-network) structure is outlined. The inputs to the structure are described in more detail.
This structure includes the use a hidden Markov model to represent the information about an opponent's hidden cards from their actions earlier in the game.
An approximate equilibrium strategy is sought by playing games of poker against itself.
Convergence is known to be an issue in self-play training for imperfect information games.
This issue is attacked by an adaptation of Dahl's "Lagging Anchor" algorithm.
The distance of a strategy from equilibrium is measured by its exploitability.
This estimated by generating a best-response to the result of a self-play training run using the same structure and learning algorithms.

http://www.ualberta.ca/~archibal/papers/sweeney.pdf


Top
 Profile E-mail  
 
Display posts from previous:  Sort by  
Post new topic Reply to topic  [ 1 post ] 


Who is online

Users browsing this forum: No registered users and 3 guests


You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot post attachments in this forum

Search for:
Jump to: