Duration
2002-
Funding  
SNF

 
Partners  


 
   

 

 

 

 

 

 

   
General Methods for Search and Reinforcement Learning
We focus on computable, practically feasible optimal search and learning algorithms based on concepts of algorithmic information theory, using principles of Levin's nonincremental universal search and Schmidhuber's very recent, incremental, optimal ordered problem solver (OOPS) for problems of optimization and prediction. OOPS is a novel, optimally fast, incremental learner that is able to improve itself through experience. It already has been shown to solve tasks on which traditional search and learning algorithms fail. It is now being applied to to problems of game-playing and robotics.
People Matteo Gagliolo

Coordinator
Juergen Schmidhuber

 

 

 
Copyright © 2003 - 2012 IDSIA. All Rights Reserved.