Transfer Learning through Analogy in Games

Thomas Hinrichs, Kenneth D. Forbus

Abstract


We report on a series of transfer learning experiments in game domains, in which we use structural analogy from one learned game to speed learning of another related game. We find that a major benefit of analogy is that it reduces the extent to which the source domain must be generalized before transfer. We describe two techniques in particular, minimal ascension and metamapping, that enable analogies to be drawn even when comparing descriptions using different relational vocabularies. Evidence for the effectiveness of these techniques is provided by a large-scale external evaluation, involving a substantial number of novel distant analogs.

Full Text:

Untitled () PDF


DOI: http://dx.doi.org/10.1609/aimag.v32i1.2332

Copyright © 2014, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.