Guiding Search in QCSP+ with Back-Propagation

The Quantified Constraint Satisfaction Problem (QCSP) has been introduced to express situations in which we are not able to control the value of some of the variables (the universal ones). Despite the expressiveness of QCSP, many problems, such as two-players games or motion planning of robots, remain difficult to express. Two more modeler-friendly frameworks have been proposed to handle this difficulty, the Strategic CSP and the QCSP. We define what we name back-propagation on QCSP. We show how back-propagation can be used to define a goal-driven value ordering heuristic and we present experimental results on board games.