Sven Koenig* and Maxim Likhachev**
*University of Southern California, **Carnegie Mellon University
Agents often have to perform repeated on-line searches as they gain additional knowledge about their environment. We describe an incremental version of A*, called Adaptive A*, that solves series of similar search problems faster than running A* repeatedly from scratch because it updates its heuristics between search episodes. It is simpler than other incremental versions of A* and thus likely easier to extend and adapt to new applications.