2015 IEEE Conference on Computational Intelligence and Games (CIG)最新文献

Personality traits in plots with nondeterministic planning for interactive storytelling 不确定互动故事情节中的人格特征

2015 IEEE Conference on Computational Intelligence and Games (CIG) Pub Date : 2015-11-05 DOI: 10.1109/CIG.2015.7317957

Fabio A. Guilherme da Silva, B. Feijó

引用次数: 1

Prediction as faster perception in a real-time fighting video game 预测是实时战斗电子游戏中更快的感知

2015 IEEE Conference on Computational Intelligence and Games (CIG) Pub Date : 2015-11-05 DOI: 10.1109/CIG.2015.7317672

K. Asayama, K. Moriyama, Ken-ichi Fukui, M. Numao

引用次数: 8

Regulation of exploration for simple regret minimization in Monte-Carlo tree search 蒙特卡洛树搜索中简单遗憾最小化的探索规则

2015 IEEE Conference on Computational Intelligence and Games (CIG) Pub Date : 2015-11-05 DOI: 10.1109/CIG.2015.7317923

Yun-Ching Liu, Yoshimasa Tsuruoka

{"title":"Regulation of exploration for simple regret minimization in Monte-Carlo tree search","authors":"Yun-Ching Liu, Yoshimasa Tsuruoka","doi":"10.1109/CIG.2015.7317923","DOIUrl":"https://doi.org/10.1109/CIG.2015.7317923","url":null,"abstract":"The application of multi-armed bandit (MAB) algorithms was a critical step in the development of Monte-Carlo tree search (MCTS). One example would be the UCT algorithm, which applies the UCB bandit algorithm. Various research has been conducted on applying other bandit algorithms to MCTS. Simple regret bandit algorithms, which aim to identify the optimal arm after a number of trials, have been of great interest in various fields in recent years. However, the simple regret bandit algorithm has the tendency to spend more time on sampling suboptimal arms, which may be a problem in the context of game tree search. In this research, we will propose combined confidence bounds, which utilize the characteristics of the confidence bounds of the improved UCB and UCB √· algorithms to regulate exploration for simple regret minimization in MCTS. We will demonstrate the combined confidence bounds bandit algorithm has better empirical performance than that of the UCB algorithm on the MAB problem. We will show that the combined confidence bounds MCTS (CCB-MCTS) has better performance over plain UCT on the game of 9 × 9 Go, and has shown good scalability. We will also show that the performance of CCB-MCTS can be further enhanced with the application of all-moves-as-first (AMAF) heuristic.","PeriodicalId":244862,"journal":{"name":"2015 IEEE Conference on Computational Intelligence and Games (CIG)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114552786","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

ACE-RL-Checkers: Improving automatic case elicitation through knowledge obtained by reinforcement learning in player agents ACE-RL-Checkers:通过在玩家代理中通过强化学习获得的知识来改进自动案例抽取

2015 IEEE Conference on Computational Intelligence and Games (CIG) Pub Date : 2015-11-05 DOI: 10.1109/CIG.2015.7317926

H. C. Neto, Rita Maria Silva Julia

{"title":"ACE-RL-Checkers: Improving automatic case elicitation through knowledge obtained by reinforcement learning in player agents","authors":"H. C. Neto, Rita Maria Silva Julia","doi":"10.1109/CIG.2015.7317926","DOIUrl":"https://doi.org/10.1109/CIG.2015.7317926","url":null,"abstract":"This work proposes a new approach that combines Automatic Case Elicitation with Reinforcement Learning applied to Checkers player agents. This type of combination brings forth the following modifications in relation to those agents that use each of these techniques in isolation: improve the random exploration performed by the Automatic Case Elicitation-based agents and introduce adaptability to the Reinforcement Learning-based agents. In line with the above, the authors present herein the ACE-RL-Checkers player agent, a hybrid system that combines the best abilities from the automatic Checkers players CHEBR and LS-VisionDraughts. CHEBR is an Automatic Case Elicitation-based agent with a learning approach that performs random exploration in the search space. These random explorations allow the agent to present an extremely adaptive and non-deterministic behavior. On the other hand, the high frequency at which decisions are made randomly (mainly in those phases in which the content of the case library is still so scarce) compromises the agent in terms of maintaining a good performance. LS-VisionDraughts is a Multi-Layer Perceptron Neural Network player trained through Reinforcement Learning. Besides having been proven efficient in making decisions, such an agent presents an inconvenience in that it is completely predictable, as the same move is always executed when presented with the same board of play. By combining the best abilities from these players, ACE-RL-Checkers uses knowledge provided from LS-VisionDraughts in order to direct random exploration of the automatic case elicitation technique to more promising regions in the search space. Therewith, the ACE-RL-Checkers gains in terms of performance as well as acquires adaptability in its decision-making - choosing moves based on the current game dynamics. Experiments carried out in tournaments involving these agents confirm the performance superiority of ACE-RL-Checkers when pitted against its adversaries.","PeriodicalId":244862,"journal":{"name":"2015 IEEE Conference on Computational Intelligence and Games (CIG)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126322380","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: 2

Making sense of emergent narratives: An architecture supporting player-triggered narrative processes 理解突发叙事:支持玩家触发叙事过程的架构

2015 IEEE Conference on Computational Intelligence and Games (CIG) Pub Date : 2015-11-05 DOI: 10.1109/CIG.2015.7317936

Simon Chauvin, G. Levieux, Jean-Yves Donnart, S. Natkin

{"title":"Making sense of emergent narratives: An architecture supporting player-triggered narrative processes","authors":"Simon Chauvin, G. Levieux, Jean-Yves Donnart, S. Natkin","doi":"10.1109/CIG.2015.7317936","DOIUrl":"https://doi.org/10.1109/CIG.2015.7317936","url":null,"abstract":"Emergent games have the particularity to allow more possible situations to emerge than progression games do. Coupled with procedural content generation techniques they also tend to increase the number of possible situations that players can encounter., However, in case the player is not creative or lucky enough these many emergent situations can have a low narrative value. This article addresses this problem through an architecture that gives players more responsibilities towards the story by allowing them to trigger Narrative Processes. A Narrative Process is a script capable of making meaningful modifications to the story in real time. Our proposed architecture relies on an Interpretation Engine whose role is to make sense of the emergent world as it is changing and inform the Narrative Processes with high level story concepts such as actors and places., We first cover the basics of emergent games and interactive narratives and then present the architecture behind the Narrative Processes as well as the Interpretation Engine. We conclude by a discussion of the potential impact of our architecture on the fundamental characteristics of emergent games.","PeriodicalId":244862,"journal":{"name":"2015 IEEE Conference on Computational Intelligence and Games (CIG)","volume":"82 12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131139283","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: 5

A strongly typed GP-based video game player 基于强类型gp的电子游戏玩家

2015 IEEE Conference on Computational Intelligence and Games (CIG) Pub Date : 2015-11-05 DOI: 10.1109/CIG.2015.7317920

Baozhu Jia, M. Ebner

引用次数: 3

“RehabConnex”: A middleware for the flexible connection of multimodal game applications with input devices used in movement therapy and physical exercising “RehabConnex”:一个中间件，用于灵活连接多模式游戏应用程序和用于运动治疗和体育锻炼的输入设备

2015 IEEE Conference on Computational Intelligence and Games (CIG) Pub Date : 2015-11-05 DOI: 10.1109/CIG.2015.7317671

A. Martin-Niedecken, René Bauer, Ralf Mauerhofer, U. Götz

{"title":"“RehabConnex”: A middleware for the flexible connection of multimodal game applications with input devices used in movement therapy and physical exercising","authors":"A. Martin-Niedecken, René Bauer, Ralf Mauerhofer, U. Götz","doi":"10.1109/CIG.2015.7317671","DOIUrl":"https://doi.org/10.1109/CIG.2015.7317671","url":null,"abstract":"“RehabConnex” is a middleware product, developed specifically to facilitate communication between hardware devices and multimodal game applications used in movement therapy and physical exercise. “RehabConnex“ is the core key development of the “IMIC”-project (Innovative Movement Therapy in Childhood), created by an interdisciplinary team of university partners to allow flexible connection between rehabilitation game environments and movement therapy robots for multimodal gameplay. “RehabConnex” both allows the patient to experience multimodal “human-robot-game-interaction” (HRGI) and helps the therapist to regulate and monitor the processes. In addition to its benefits for a broad range of game-based rehabilitation scenarios, the development of “RehabConnex” opens up similar perspectives for its use in multimodal game-based physical exercising (Exergames) and for other “human-device-game-interactions” (HDGI). “RehabConnex” yields innovative research questions on the general effects of multimodal environments.","PeriodicalId":244862,"journal":{"name":"2015 IEEE Conference on Computational Intelligence and Games (CIG)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133142401","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: 0

Learning a game commentary generator with grounded move expressions 学习一个游戏评论生成器与接地移动表达式

2015 IEEE Conference on Computational Intelligence and Games (CIG) Pub Date : 2015-11-05 DOI: 10.1109/CIG.2015.7317930

Hirotaka Kameko, Shinsuke Mori, Yoshimasa Tsuruoka

引用次数: 17

EnHiC: An enforced hill climbing based system for general game playing EnHiC:一般游戏的强制爬山系统

2015 IEEE Conference on Computational Intelligence and Games (CIG) Pub Date : 2015-11-05 DOI: 10.1109/CIG.2015.7317907

Amin Babadi, B. Omoomi, G. Kendall

引用次数: 5

Generation of an arbitrary shaped large maze by assembling mazes 通过组合迷宫生成任意形状的大型迷宫

2015 IEEE Conference on Computational Intelligence and Games (CIG) Pub Date : 2015-11-05 DOI: 10.1109/CIG.2015.7317901

Cheong-mok Bae, Eun Kwang Kim, Jongchan Lee, Kyung-Joong Kim, J. Na

引用次数: 1