Transfer Learning by Inductive Logic Programming

被引：1

作者：

Sato, Yuichiro ^{[1
]}

Iida, Hiroyuki ^{[1
]}

van den Herik, H. J. ^{[2
]}

机构：

[1] Japan Adv Inst Sci & Technol, Sch Informat Sci, 1-1 Asahidai, Nomi, Ishikawa, Japan

[2] Leiden Inst Adv Comp Sci, NL-2300 RA Leiden, Netherlands

来源：

ADVANCES IN COMPUTER GAMES, ACG 2015 | 2015年 / 9525卷

关键词：

D O I：

10.1007/978-3-319-27992-3_20

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we propose a Transfer Learning method by Inductive Logic Programing for games. We generate general knowledge from a game, and specify the knowledge so that it is applicable in another game. This is called Transfer Learning. We show the working of Transfer Learning by taking knowledge from Tic-tac-toe and transfer it to Connect4 and Connect5. For Connect4 the number of Heuristic functions we developed is 30; for Connect5 it is 20.

引用

页码：223 / 234

页数：12

共 12 条

[1] [Anonymous], 2006, Technical Report LG- 2006-01
[2] [Anonymous], 2007, Proceedings of the AAAI National Conference on Artificial Intelligence
[3] CADIAPLAYER: A Simulation-Based General Game Player
Bjornsson, Yngvi
Finnsson, Hilmar
[J]. IEEE TRANSACTIONS ON COMPUTATIONAL INTELLIGENCE AND AI IN GAMES, 2009, 1 (01) : 4 - 15
[4] Transfer Learning through Analogy in Games
Hinrichs, Thomas R.
Forbus, Kenneth D.
[J]. AI MAGAZINE, 2011, 32 (01) : 70 - 83
[5] Mehat J., 2010, BOARD GAM STUD C
[6] Michulke D, 2009, LECT NOTES ARTIF INT, V5782, P95, DOI 10.1007/978-3-642-04174-7_7
[7] Mitchell T. M., 1986, Machine Learning, V1, P47, DOI 10.1007/BF00116250
[8] INVERSE ENTAILMENT AND PROGOL
MUGGLETON, S
[J]. NEW GENERATION COMPUTING, 1995, 13 (3-4) : 245 - 286
[9] INDUCTIVE LOGIC PROGRAMMING - THEORY AND METHODS
MUGGLETON, S
DERAEDT, L
[J]. JOURNAL OF LOGIC PROGRAMMING, 1994, 20 : 629 - 679
[10] Muggleton S, 2010, LECT NOTES ARTIF INT, V5989, P123, DOI 10.1007/978-3-642-13840-9_12

← 1 2 →