Extended Abstract: Learning Search Strategies

Daishi Harada and Stuart Russell

The goal of this paper is to consider yet another framework in which real-world control problems may be solved. The benefit of the framework, compared to the other approaches, is that the computational process/controller is explicitly modelled. What this means is that a solution to a problem within our framework can by definition be implemented, and in addition, will be the bounded optimal solution to the problem. In this paper we consider the case when we select search as our model of computation.


This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.