Comparative Analysis of Existing Architectures for General Game Agents

被引：1

作者：

Hosu, Ionel-Alexandru ^{[1
]}

Urzica, Andreea ^{[1
]}

机构：

[1] Univ Politehn Bucuresti, Fac Automat Control & Comp Sci, Bucharest, Romania

来源：

2015 17TH INTERNATIONAL SYMPOSIUM ON SYMBOLIC AND NUMERIC ALGORITHMS FOR SCIENTIFIC COMPUTING (SYNASC) | 2016年

关键词：

convolutional neural networks; Q-learning; model-free algorithms; neuroevolution; games;

D O I：

10.1109/SYNASC.2015.48

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

This paper addresses the development of general purpose game agents able to learn a vast number of games using the same architecture. The article analyzes the main existing approaches to general game playing, reviews their performance and proposes future research directions. Methods such as deep learning, reinforcement learning and evolutionary algorithms are considered for this problem. The testing platform is the popular video game console Atari 2600. Research into developing general purpose agents for games is closely related to achieving artificial general intelligence (AGI).

引用

页码：257 / 260

页数：4

共 50 条

[41] Virtual Reality Sickness Mitigation Methods: A Comparative Study in a Racing Game
Shi, Rongkai
Liang, Hai-Ning
Wu, Yu
Yu, Difeng
Xu, Wenge
PROCEEDINGS OF THE ACM ON COMPUTER GRAPHICS AND INTERACTIVE TECHNIQUES, 2021, 4 (01)
[42] HyperNEAT-GGP: A HyperNEAT-based Atari General Game Player
Hausknecht, Matthew
Khandelwal, Piyush
Miikkulainen, Risto
Stone, Peter
PROCEEDINGS OF THE FOURTEENTH INTERNATIONAL CONFERENCE ON GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE, 2012, : 217 - 224
[43] Self-Adaptive Monte Carlo Tree Search in General Game Playing
Sironi, Chiara F.
Liu, Jialin
Winands, Mark H. M.
IEEE TRANSACTIONS ON GAMES, 2020, 12 (02) : 132 - 144
[44] OSNR game optimization with link capacity constraints in general topology WDM networks
Pan, Yan
Pavel, Lacra
OPTICAL SWITCHING AND NETWORKING, 2014, 11 : 1 - 15
[45] Learning to Generalize With Object-Centric Agents in the Open World Survival Game Crafter
Stanic, Aleksandar
Tang, Yujin
Ha, David
Schmidhuber, Jurgen
IEEE TRANSACTIONS ON GAMES, 2024, 16 (02) : 384 - 395
[46] Altruism and Selfishness in Believable Game Agents: Deep Reinforcement Learning in Modified Dictator Games
Daylamani-Zad, Damon
Angelides, Marios C.
IEEE TRANSACTIONS ON GAMES, 2021, 13 (03) : 229 - 238
[47] Q-Learning with Naive Bayes Approach Towards More Engaging Game Agents
Yilmaz, Osman
Celikcan, Ufuk
2018 INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND DATA PROCESSING (IDAP), 2018,
[48] A sensitivity analysis of matching coin game strategies
Shyryayev, I
Jacobson, SH
MATHEMATICAL AND COMPUTER MODELLING, 2005, 41 (6-7) : 735 - 747
[49] Benchmark Analysis of Popular ImageNet Classification Deep CNN Architectures
Muhammed, Mustafa Alghali Elsaid
Ahmed, Ahmed Abdalazeem
Khalid, Tarig Ahmed
PROCEEDINGS OF THE 2017 INTERNATIONAL CONFERENCE ON SMART TECHNOLOGIES FOR SMART NATION (SMARTTECHCON), 2017, : 902 - 907
[50] Cognitive Analysis of Educational Games: The Number Game
van der Maas, Han L. J.
Nyamsuren, Enkhbold
TOPICS IN COGNITIVE SCIENCE, 2017, 9 (02) : 395 - 412

← 1 2 3 4 5 →