Duration
2001-
Funding  
SNF

 
Partners  


 
   

 

 

 

 

 

 

   
Unification of Inductive Inference and sequential decision theory
The goal is to develop a universal theory of sequential decision making akin to Solomonoff's celebrated universal theory of induction. Solomonoff derived an optimal way of predicting future data, given previous observations, provided the data is sampled from a recursively computable probability distribution. The goal is to extend this approach to derive an optimal rational reinforcement learning agent embedded in an unknown environment sampled from a computable distribution. One remarkable and surprising by-product of this research is the asymptotically fastest and shortest algorithm for solving ANY well-defined problem.
People Marcus Hutter

Coordinator
Juergen Schmidhuber

 

 

 
Copyright © 2003 - 2012 IDSIA. All Rights Reserved.