Learning Game-Specific Spatially-Oriented Heuristics |
| |
Authors: | Susan L Epstein Jack Gelfand Esther Lock |
| |
Affiliation: | (1) Department of Computer Science, Hunter College and The Graduate School, The City University of New York, New York, NY, 10021;(2) Department of Psychology, Princeton University, Princeton, NJ, 08544;(3) Department of Computer Science, The Graduate School of The City University of New York, New York, NY, 10036 |
| |
Abstract: | This paper describes an architecture that begins with enough general knowledge to play any board game as a novice, and then shifts its decision-making emphasis to learned, game-specific, spatially-oriented heuristics. From its playing experience, it acquires game-specific knowledge about both patterns and spatial concepts. The latter are proceduralized as learned, spatially-oriented heuristics. These heuristics represent a new level of feature aggregation that effectively focuses the program's attention. While training against an external expert, the program integrates these heuristics robustly. After training it exhibits both a new emphasis on spatially-oriented play and the ability to respond to novel situations in a spatially-oriented manner. This significantly improves performance against a variety of opponents. In addition, we address the issue of context on pattern learning. The procedures described here move toward learning spatially-oriented heuristics for autonomous programs in other spatial domains. |
| |
Keywords: | machine learning game playing spatial cognition extensible architectures |
本文献已被 SpringerLink 等数据库收录! |
|