Knowledge-based fast evolutionary MCTS for general video game playing

Knowledge-based fast evolutionary MCTS for general video game playing
复制标题

适用于一般视频游戏的基于知识的快速进化 MCTS

DOI:
10.1109/cig.2014.6932868
复制
发表时间:
2014
期刊:
--
影响因子:
--
通讯作者:
Perez D
Perez D
中科院分区:
--
文献类型:
--
作者:
Perez D

文献摘要

参考文献

被引文献

相似文献

一般的视频游戏是一个游戏AI领域,其中依赖于游戏的领域知识的使用非常有限,甚至不存在。当试图创建能够玩不同游戏集的代理时,这带来了明显的困难。从更广泛的角度来看,这个问题可以作为一般人工智能领域的介绍。本文探讨了一种简单的蒙特卡罗树搜索算法的性能,并分析了在处理这类情况时遇到的主要困难。修改,提出了克服这些问题,加强算法的能力,收集和发现知识,并利用过去的经验。结果表明,该算法的性能显着提高,但仍有未解决的问题,需要进一步的研究。本研究中采用的框架是公开的,并将用于2014年IEEE计算智能和游戏会议的通用视频游戏比赛。
General Video Game Playing is a game AI domain in which the usage of game-dependent domain knowledge is very limited or even non existent. This imposes obvious difficulties when seeking to create agents able to play sets of different games. Taken more broadly, this issue can be used as an introduction to the field of General Artificial Intelligence. This paper explores the performance of a vanilla Monte Carlo Tree Search algorithm, and analyzes the main difficulties encountered when tackling this kind of scenarios. Modifications are proposed to overcome these issues, strengthening the algorithm's ability to gather and discover knowledge, and taking advantage of past experiences. Results show that the performance of the algorithm is significantly improved, although there remain unresolved problems that require further research. The framework employed in this research is publicly available and will be used in the General Video Game Playing competition at the IEEE Conference on Computational Intelligence and Games in 2014.
DOI: 10.1109/cig.2013.6633639
发表时间: 2013-10
期刊: 2013 IEEE Conference on Computational Inteligence in Games (CIG)
影响因子: --
作者:
Atif M. Alhejali;S. Lucas
通讯作者: Atif M. Alhejali;S. Lucas
DOI: 10.1007/s13218-010-0077-4
发表时间: 2010-12
期刊: KI - Künstliche Intelligenz
影响因子: --
作者:
Maximilian Möller;M. Lindauer;Martin Wegner;Torsten Schaub
通讯作者: Maximilian Möller;M. Lindauer;Martin Wegner;Torsten Schaub
用于玩 Atari 2600 主机游戏的独立于游戏的 AI 代理
DOI: --
发表时间: 2010
期刊:
影响因子: --
作者:
Yavar Naddaf
通讯作者: Yavar Naddaf
蒙特卡罗树搜索的快速进化适应
DOI: --
发表时间: 2014
期刊: EvoApplications
影响因子: --
作者:
S. Lucas;Spyridon Samothrakis;Diego Perez Liebana
通讯作者: Diego Perez Liebana
一般视频游戏
DOI: --
发表时间: 2013
期刊: Artificial and Computational Intelligence in Games
影响因子: --
作者:
J. Levine;C. Congdon;M. Ebner;G. Kendall;S. Lucas;R. Miikkulainen;T. Schaul;Tommy Thompson
通讯作者: Tommy Thompson