2012 IEEE Conference on Computational Intelligence and Games (CIG)最新文献_第2页

Comparison of different selection strategies in Monte-Carlo Tree Search for the game of Tron Tron游戏中蒙特卡罗树搜索中不同选择策略的比较

2012 IEEE Conference on Computational Intelligence and Games (CIG) Pub Date : 2012-12-06 DOI: 10.1109/CIG.2012.6374162

Pierre Perick, D. St-Pierre, Francis Maes, D. Ernst

{"title":"Comparison of different selection strategies in Monte-Carlo Tree Search for the game of Tron","authors":"Pierre Perick, D. St-Pierre, Francis Maes, D. Ernst","doi":"10.1109/CIG.2012.6374162","DOIUrl":"https://doi.org/10.1109/CIG.2012.6374162","url":null,"abstract":"Monte-Carlo Tree Search (MCTS) techniques are essentially known for their performance on turn-based games, such as Go, for which players have considerable time for choosing their moves. In this paper, we apply MCTS to the game of Tron, a simultaneous real-time two-player game. The fact that players have to react fast and that moves occur simultaneously creates an unusual setting for MCTS, in which classical selection policies such as UCB1 may be suboptimal. In this paper, we perform an empirical comparison of a wide range of selection policies for MCTS applied to Tron, with both deterministic policies (UCB1, UCBl-Tuned, UCB-V, UCB-Minimal, OMC-Deterministic, MOSS) and stochastic policies (ϵn-greedy, EXP3, Thompson Sampling, OMC-Stochastic, PBBM). From the experiments, we observe that UCBl-Tuned has the best behavior shortly followed by UCB1. Even if UCB-Minimal is ranked fourth, this is a remarkable result for this recently introduced selection policy found through automatic discovery of good policies on generic multi-armed bandit problems. We also show that deterministic policies perform better than stochastic ones for this problem.","PeriodicalId":288052,"journal":{"name":"2012 IEEE Conference on Computational Intelligence and Games (CIG)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115372276","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 40

Learning visual composition preferences from an annotated corpus generated through gameplay 从通过游戏生成的注释语料库中学习视觉构图偏好

2012 IEEE Conference on Computational Intelligence and Games (CIG) Pub Date : 2012-12-06 DOI: 10.1109/CIG.2012.6374178

Reid Swanson, D. Escoffery, A. Jhala

{"title":"Learning visual composition preferences from an annotated corpus generated through gameplay","authors":"Reid Swanson, D. Escoffery, A. Jhala","doi":"10.1109/CIG.2012.6374178","DOIUrl":"https://doi.org/10.1109/CIG.2012.6374178","url":null,"abstract":"This paper describes a game called Panorama, designed to facilitate data collection to study visual composition preferences. Design considerations for Panorama, implementation of composition rules, and data collection for an experiment to learn individual and collective preferences is described. Images taken through gameplay in Panorama are automatically scored for composition quality and contribute to a corpus of domain-specific virtual photographs annotated by visual features and scores. Scores in Panorama represent rules of good composition from photography textbooks. In the current version, Panorama scores photographs along balance, thirds alignment, symmetry, and spacing dimensions. Pairwise preference rankings are collected on images from this corpus through crowd-sourcing. Results are presented from data on relative pairwise rankings on the images to learn individual as well as general composition preferences over features annotated in Panorama images. This work seeks to extend the ability of AI systems to learn and reason about high-level aesthetic features of photographs that could be utilized for various procedural camera control and aesthetic layout algorithms in video games.","PeriodicalId":288052,"journal":{"name":"2012 IEEE Conference on Computational Intelligence and Games (CIG)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115011652","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 15

Adaptive bots for real-time strategy games via map characterization 基于地图特征的即时战略游戏的自适应机器人

2012 IEEE Conference on Computational Intelligence and Games (CIG) Pub Date : 2012-12-06 DOI: 10.1109/CIG.2012.6374185

A. Fernández-Ares, P. García-Sánchez, A. García, J. J. M. Guervós

引用次数: 19

Special tactics: A Bayesian approach to tactical decision-making 特殊战术:战术决策的贝叶斯方法

2012 IEEE Conference on Computational Intelligence and Games (CIG) Pub Date : 2012-12-06 DOI: 10.1109/CIG.2012.6374184

Gabriel Synnaeve, P. Bessière

引用次数: 36

Statistical analyses of representation choice in level generation 关卡生成中表征选择的统计分析

2012 IEEE Conference on Computational Intelligence and Games (CIG) Pub Date : 2012-12-06 DOI: 10.1109/CIG.2012.6374171

C. McGuinness

引用次数: 6

Evaluating the enjoyability of the ghosts in Ms Pac-Man 评估《吃豆人女士》中幽灵的乐趣

2012 IEEE Conference on Computational Intelligence and Games (CIG) Pub Date : 2012-12-06 DOI: 10.1109/CIG.2012.6374180

Wichit Sombat, Philipp Rohlfshagen, S. Lucas

{"title":"Evaluating the enjoyability of the ghosts in Ms Pac-Man","authors":"Wichit Sombat, Philipp Rohlfshagen, S. Lucas","doi":"10.1109/CIG.2012.6374180","DOIUrl":"https://doi.org/10.1109/CIG.2012.6374180","url":null,"abstract":"The video games industry is one of the fastest-growing industries in the world, bolstered by sophisticated technology in gaming consoles and modern trends such as mobile and social gaming. The goal of most video games is to entertain the gamer and in most games this stems from the interaction between the gamer and the non-player characters (NPCs): it is no longer sufficient for a game to be visually appealing but instead, the gamer must be challenged at the right level of difficulty to be engaged by the game. It is thus necessary to develop suitable NPCs that are fun to play against and the realm of computational intelligence offers a variety of techniques to do so. However, the perception of fun is clearly subjective and indeed, difficult to quantify. In this paper we make use of the Ms Pac-Man vs Ghosts gaming competition to gather and analyse data from human gamers regarding their preference of opponent: each gamer plays two games against different ghost teams, indicating their preference at the end. We subsequently use this data to establish which ghost teams are generally preferred and demonstrate that there are measurable differences between these ghost teams. These differences are sufficient to group the ghosts into different categories with a good degree of accuracy. This work is a first step in better understanding the attributes required by NPCs for players to be engaged.","PeriodicalId":288052,"journal":{"name":"2012 IEEE Conference on Computational Intelligence and Games (CIG)","volume":"199 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132903803","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 7

A model-based cell decomposition approach to on-line pursuit-evasion path planning and the video game Ms. Pac-Man 基于模型的单元分解方法用于在线追逃路径规划和电子游戏《吃豆人小姐》

2012 IEEE Conference on Computational Intelligence and Games (CIG) Pub Date : 2012-12-06 DOI: 10.1109/CIG.2012.6374167

Greg Foderaro, Ashleigh Swingler, S. Ferrari

引用次数: 18

Emotional behavior trees 情绪行为树

2012 IEEE Conference on Computational Intelligence and Games (CIG) Pub Date : 2012-12-06 DOI: 10.1109/CIG.2012.6374177

Anja Johansson, Pierangelo Dell'Acqua

引用次数: 28

Potential-field based navigation in StarCraft 《星际争霸》中基于潜在场的导航

2012 IEEE Conference on Computational Intelligence and Games (CIG) Pub Date : 2012-12-06 DOI: 10.1109/CIG.2012.6374181

Johan Hagelbäck

引用次数: 45

Aesthetic Terrain Programs database for creativity assessment 审美地形程序数据库的创造力评估

2012 IEEE Conference on Computational Intelligence and Games (CIG) Pub Date : 2012-12-06 DOI: 10.1109/CIG.2012.6374176

Miguel Frade, F. F. Vega, C. Cotta

引用次数: 6