| Terry van Belle. A New Approach to Genetic-Based Automatic Feature Discovery. Master's thesis, University of Alberta, 1995. |
....techniques. However, in Awari we have a radically di erent situation. The quality of an evaluation function can be measured directly against the perfect information in the endgame databases. 3. 1 Previous work Previous attempts to mine endgame databases include research done by Terry van Belle [vB95] and Paul Utgo et al. UP97,UP98] Van Belle attempted to apply genetic algorithms to checkers endgame databases, which proved to be unsuccessful. Utgo developed the ELF learning algorithm, which was able to make progress in identifying features in checkers by using reinforcement learning ....
Terry van Belle. A New Approach to Genetic-Based Automatic Feature Discovery. Master's thesis, University of Alberta, 1995.
No context found.
Terry van Belle. A New Approach to Genetic-Based Automatic Feature Discovery. Master's thesis, University of Alberta, 1995. http://www.cs.ualberta.ca/~jonathan/.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC