Playing Mastermind Game by using Reinforcement Learning

被引：2

作者：

Lu, Wei-Fu ^{[1
]}

Yang, Ji-Kai ^{[1
]}

Chu, Hsueh-Ting ^{[1
]}

机构：

[1] Asia Univ, Dept CSIE, Taichung, Taiwan

来源：

2017 FIRST IEEE INTERNATIONAL CONFERENCE ON ROBOTIC COMPUTING (IRC) | 2017年

关键词：

mastermind; machine learning; reinforcement learning; Monte-Carlo methods; Sarsa(lambda);

D O I：

10.1109/IRC.2017.54

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 play the Mastermind game by using strategies of reinforcement learning. Monte-Carlo method and Sarsa(lambda) algorithms are used to obtain the optimal policy for finding opponent's secrete code and the optimal policy for constructing our secrete code. The experimental results show that of our approach's expected number of guessing is 4.294, which is better than most part's 4.373. In secret code construction, we increase numbers of guessing of other methods successfully, such as the expected number of guessing of most part increasing to 4.635 from 4.373.

引用

页码：418 / 421

页数：4

共 50 条

[1] Playing the Game of Congklak with Reinforcement Learning
Kasim, Muhammad Firmansyah
[J]. PROCEEDINGS OF 2016 8TH INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY AND ELECTRICAL ENGINEERING (ICITEE), 2016,
[2] Social Reinforcement Learning in Game Playing
Kiourt, Chairi
Kalles, Dimitris
[J]. 2012 IEEE 24TH INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE (ICTAI 2012), VOL 1, 2012, : 322 - 326
[3] Modular Reinforcement Learning for Playing the Game of Tron
Jeon, Mingi
Lee, Jay
Ko, Sang-Ki
[J]. IEEE ACCESS, 2022, 10 : 63394 - 63402
[4] Deep Reinforcement Learning for General Game Playing
Goldwaser, Adrian
Thielscher, Michael
[J]. THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 1701 - 1708
[5] General game-playing and reinforcement learning
Levinson, R
[J]. COMPUTATIONAL INTELLIGENCE, 1996, 12 (01) : 155 - 176
[6] Comparison of Deep Reinforcement Learning Approaches for Intelligent Game Playing
Jeerige, Anoop
Bein, Doina
Verma, Abhishek
[J]. 2019 IEEE 9TH ANNUAL COMPUTING AND COMMUNICATION WORKSHOP AND CONFERENCE (CCWC), 2019, : 366 - 371
[7] Playing a Strategy Game with Knowledge-Based Reinforcement Learning
Voss V.
Nechepurenko L.
Schaefer R.
Bauer S.
[J]. SN Computer Science, 2020, 1 (2)
[8] Hierarchical Reinforcement Learning for Playing a Dynamic Dungeon Crawler Game
Niel, Remi
Wiering, Marco A.
[J]. 2018 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (IEEE SSCI), 2018, : 1159 - 1166
[9] Research on Game-Playing Agents Based on Deep Reinforcement Learning
Zhao, Kai
Song, Jia
Luo, Yuxie
Liu, Yang
[J]. ROBOTICS, 2022, 11 (02)
[10] Playing a FPS Doom Video Game with Deep Visual Reinforcement Learning
Feng Adil Khan
Shaohui Jiang
Ibrahim Liu
[J]. Automatic Control and Computer Sciences, 2019, 53 : 214 - 222

← 1 2 3 4 5 →