Learning heuristics in search domains

Mehdi Samadi, Ariel Felner, Jonathan Schaeffer

Research output: Contribution to conferencePaperpeer-review


Heuristic functions for single-agent search applications estimate the cost of the optimal solution. When multiple heuristics exist, taking their maximum is an effective way to combine them. A new technique is introduced for combining multiple heuristic values. Inspired by the evaluation functions used in two-player games, the different heuristics in a singleagent application are treated as features of the problem domain. An ANN is used to combine these features into a single heuristic value. This idea has been implemented for the sliding-tile puzzle and the 4-peg Towers of Hanoi, two classic single-agent search domains. Experimental results show that this technique can lead to a large reduction in the search effort at a small cost in the quality of the solution obtained. To show the applicability of our learning approach we have also implemented it on the game of chess as a benchmark of two players games. Our experimental results show that the proposed learning strategy is effective in winning against an opponent who offers its best survival defense using Nalimov database of best endgame moves.

Original languageEnglish
StatePublished - 1 Dec 2008
Event1st International Symposium on Combinatorial Search, SoCS 2008 - Chicago, IL, United States
Duration: 13 Jul 200814 Jul 2008


Conference1st International Symposium on Combinatorial Search, SoCS 2008
Country/TerritoryUnited States
CityChicago, IL

ASJC Scopus subject areas

  • Computer Networks and Communications


Dive into the research topics of 'Learning heuristics in search domains'. Together they form a unique fingerprint.

Cite this