Training Neural Networks to Play Backgammon Variants Using Reinforcement Learning

被引：0

作者：

Papahristou, Nikolaos ^{[1
]}

Refanidis, Ioannis ^{[1
]}

机构：

[1] Univ Macedonia, Dept Appl Informat, Thessaloniki 54006, Greece

来源：

APPLICATIONS OF EVOLUTIONARY COMPUTATION, PT I | 2011年 / 6624卷

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Backgammon is a board game that has been studied considerably by computer scientists. Apart from standard backgammon, several yet unexplored variants of the game exist, which use the same board, number of checkers, and dice but may have different rules for moving the checkers, starting positions and movement direction. This paper studies two popular variants in Greece and neighboring countries, named Fevga and Plakoto. Using reinforcement learning and Neural Network function approximation we train agents that learn a game position evaluation function for these games. We show that the resulting agents significantly outperform the open-source program Tavli3D.

引用

页码：113 / 122

页数：10

共 50 条

[21] Network parameter setting for reinforcement learning approaches using neural networks
Yamada, Kazuaki
Ohkura, Kazuhiro
Nihon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C, 2012, 78 (792): : 2950 - 2961
[22] Network Parameter Setting for Reinforcement Learning Approaches Using Neural Networks
Yamada, Kazuaki
JOURNAL OF ADVANCED COMPUTATIONAL INTELLIGENCE AND INTELLIGENT INFORMATICS, 2011, 15 (07) : 822 - 830
[23] Optimizing parameter settings for hopfield neural networks using reinforcement learning
Rbihou, Safae
Joudar, Nour-Eddine
Haddouch, Khalid
EVOLVING SYSTEMS, 2024, 15 (06) : 2419 - 2440
[24] Accelerated reinforcement learning control using modified CMAC neural networks
Xu, X
Hu, DW
He, HG
ICONIP'02: PROCEEDINGS OF THE 9TH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING: COMPUTATIONAL INTELLIGENCE FOR THE E-AGE, 2002, : 2575 - 2578
[25] A reinforcement learning algorithm for a class of dynamical environments using neural networks
Murata, M
Ozawa, S
SICE 2003 ANNUAL CONFERENCE, VOLS 1-3, 2003, : 2004 - 2009
[26] A Transfer Approach Using Graph Neural Networks in Deep Reinforcement Learning
Yang, Tianpei
You, Heng
Hao, Jianye
Zheng, Yan
Taylor, Matthew E.
THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 15, 2024, : 16352 - 16360
[27] Attitude Control of a Nanosatellite system using Reinforcement Learning and Neural Networks
Yadava, Deigant
Hosangadi, Raunak
Krishna, Sai
Paliwal, Pranjal
Jain, Avi
2018 IEEE AEROSPACE CONFERENCE, 2018,
[28] Incorporating Expert Advice into Reinforcement Learning Using Constructive Neural Networks
Ollington, Robert
Vamplew, Peter
Swanson, John
CONSTRUCTIVE NEURAL NETWORKS, 2009, 258 : 207 - +
[29] On-line reinforcement learning using cascade constructive neural networks
Vamplew, P
Ollington, R
KNOWLEDGE-BASED INTELLIGENT INFORMATION AND ENGINEERING SYSTEMS, PT 3, PROCEEDINGS, 2005, 3683 : 562 - 568
[30] Learning to Play Othello With Deep Neural Networks
Liskowski, Pawel
Jaskowski, Wojciech
Krawiec, Krzysztof
IEEE TRANSACTIONS ON GAMES, 2018, 10 (04) : 354 - 364

← 1 2 3 4 5 →