By Topic

2011 IEEE Conference on Computational Intelligence and Games (CIG'11)

Aug. 31 2011-Sept. 3 2011

Filter Results

Displaying Results 1 - 25 of 56
  • Preface

    Publication Year: 2011, Page(s):F-1 - F-2
    Request permission for commercial reuse | PDF file iconPDF (288 KB)
    Freely Available from IEEE
  • Authors index

    Publication Year: 2011, Page(s):A-1 - A-5
    Request permission for commercial reuse | PDF file iconPDF (317 KB)
    Freely Available from IEEE
  • Competitions

    Publication Year: 2011, Page(s):B-1 - B-2
    Request permission for commercial reuse | PDF file iconPDF (310 KB) | HTML iconHTML
    Freely Available from IEEE
  • Keynotes: Data mining and machine learning applications in MMOs

    Publication Year: 2011, Page(s):C-1 - C-3
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (323 KB)

    Summary form only given. Database abstractions, such as TinyDB [1] and TikiriDB [2], have been used successfully in wireless sensor networks (WSN). These abstractions provide an interface for SQL like queries to extract data from sensors. This has proven to be a convenient programming interface in these environments. However, a relational database model that guarantees ACID (Atomicity, Consistency... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • NCsoft special session: NCsoft, connecting the world with entertainment

    Publication Year: 2011, Page(s): D-1
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (283 KB)

    Summary form only given. Near-Threshold Voltage (NTV) operation of a CMOS design is defined as the voltage-frequency operating point where the energy consumed per compute operation (pJ/op) reaches a minimum, or the energy efficiency (Mops/Watt) peaks. Typically, this operating voltage is above the nominal threshold voltage of the transistor. The peak efficiency is achieved by a balance of switchin... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Organizing Committee

    Publication Year: 2011, Page(s):E-1 - E-2
    Request permission for commercial reuse | PDF file iconPDF (312 KB)
    Freely Available from IEEE
  • Program

    Publication Year: 2011, Page(s):G-1 - G-6
    Request permission for commercial reuse | PDF file iconPDF (347 KB)
    Freely Available from IEEE
  • Sponsors

    Publication Year: 2011, Page(s):H-1 - H-2
    Request permission for commercial reuse | PDF file iconPDF (328 KB)
    Freely Available from IEEE
  • Table of contents

    Publication Year: 2011, Page(s):I-1 - I-4
    Request permission for commercial reuse | PDF file iconPDF (334 KB)
    Freely Available from IEEE
  • Tutorials: Cultural Algorithms: Incorporating social intelligence into virtual worlds

    Publication Year: 2011, Page(s):J-1 - J-5
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (344 KB) | HTML iconHTML

    These tutorials discuss the following: cultural algorithms: incorporating social intelligence into virtual worlds; automating the analysis of evolved agents; experience-driven procedural content generation; and experimentation in CI-affected games research. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Enhanced cooperation in the N-person iterated snowdrift game through tag mediation

    Publication Year: 2011, Page(s):1 - 8
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (649 KB) | HTML iconHTML

    This paper investigates whether tags can elevate cooperation levels in N-player iterated evolutionary snowdrift games. Tags give agents the ability to form groups that can prosper under certain circumstances. Previous work showed tags promote cooperation in iterated prisoner's dilemma games but no work has seen if they enhance cooperation in snowdrift games. We studied different tag models used in... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Monte-Carlo approach for the endgame of Ms. Pac-Man

    Publication Year: 2011, Page(s):9 - 15
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1059 KB) | HTML iconHTML

    Ms. Pac-Man is a challenging video game which provides an interesting platform for artificial intelligence and computational intelligence research. This paper introduces the novel concept of path testing and reports an effective Monte-Carlo approach to develop an endgame module of an intelligent agent that plays the game. Our experimental results show that the proposed method often helps Ms. Pac-M... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Incorporating required structure into tiles

    Publication Year: 2011, Page(s):16 - 23
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3430 KB) | HTML iconHTML

    Search based procedural content generation uses search techniques to locate high-quality content elements for use in games. This study extends an evolutionary-computation based system to generate tiles used to assemble floor plans for levels in a video game as well as evolving assembly plans. The separate evolution of assembly plans and tiles yields a decomposition of the level generation problem ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optimization of an evaluation function of the 4-sided dominoes game using a genetic algorithm

    Publication Year: 2011, Page(s):24 - 30
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (771 KB) | HTML iconHTML

    In 4-sided dominoes, the popular way of playing dominoes in Amazonas State, the strategies used for the game are more complex than those adopted in the more traditional 2-sided dominoes, the most popular dominoes game played in Brazil. This work presents the optimization of an evaluation function for the best move in 4-sided dominoes using a genetic algorithm. The evaluation function is composed o... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Frame selection using iterative grammatical evolution for automatic comic generation from game logs

    Publication Year: 2011, Page(s):31 - 38
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (5258 KB) | HTML iconHTML

    Recently, we developed a system that visualizes a game play, from its game log, with a comic-style representation. In that system, comic frames are selected based on their interaction levels without considering users' interests. In this paper, we tackle this issue by proposing an interactive frame-selection method that adopts interactive evolutionary computation (IEC) for evolving conditional rule... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Monte-Carlo tree search in Ms. Pac-Man

    Publication Year: 2011, Page(s):39 - 46
    Cited by:  Papers (18)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (946 KB) | HTML iconHTML

    This paper proposes a method for solving the problem of avoiding pincer moves of the ghosts in the game of Ms. Pac-Man to enhance the chance of survival for Ms. Pac-Man. To achieve this, the approach of using the UCT (UCB applied to trees) algorithm, a Monte-Carlo tree search algorithm that proved to be successful with a computer game of Go, was employed. The UCT algorithm is one of the tree searc... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Towards gaze-controlled platform games

    Publication Year: 2011, Page(s):47 - 54
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (722 KB) | HTML iconHTML

    This paper introduces the concept of using gaze as a sole modality for fully controlling player characters of fast-paced action computer games. A user experiment is devised to collect gaze and gameplay data from subjects playing a version of the popular Super Mario Bros platform game. The initial analysis shows that there is a rather limited grid around Mario where the efficient player focuses her... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • User-preference-based automated level generation for platform games

    Publication Year: 2011, Page(s):55 - 62
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (819 KB) | HTML iconHTML

    Level content generation in the genre of platform games, so far, has focused primarily on the typical, tactile-skill based levels with simple left to right movement. In this paper, we present a level generation method that expands these standard kinds of levels by integrating puzzle based content that requires the player to explore the level in order to solve it. With these choices comes the need ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hormonal systems for prisoners dilemma agents

    Publication Year: 2011, Page(s):63 - 70
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1126 KB) | HTML iconHTML

    A large number of studies have evolved agents to play the iterated prisoners dilemma. This study models a novel type of interaction, called the Shopkeeper model of interaction, in which a state conditioned agent interacts with a series of other agents without resetting its internal state. This is intended to simulate the situation in which a shopkeeper interacts with a series of customers. This st... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neuroevolutionary constrained optimization for content creation

    Publication Year: 2011, Page(s):71 - 78
    Cited by:  Papers (10)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1095 KB) | HTML iconHTML

    This paper presents a constraint-based procedural content generation (PCG) framework used for the creation of novel and high-performing content. Specifically, we examine the efficiency of the framework for the creation of spaceship design (hull shape and spaceship attributes such as weapon and thruster types and topologies) independently of game physics and steering strategies. According to the pr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Discount and speed/execution tradeoffs in Markov Decision Process games

    Publication Year: 2011, Page(s):79 - 86
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1387 KB) | HTML iconHTML

    We study Markov Decision Process (MDP) games with the usual ±1 reinforcement signal. We consider the scenario in which the goal of the game, rather than just winning, is to maximize the number of wins in an allotted period of time (or maximize the expected reward in the same period). In the reinforcement learning literature, this type of tradeoff is often handled by tuning the discount para... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Determinization and information set Monte Carlo Tree Search for the card game Dou Di Zhu

    Publication Year: 2011, Page(s):87 - 94
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (749 KB) | HTML iconHTML

    Determinization is a technique for making decisions in games with stochasticity and/or imperfect information by sampling instances of the equivalent deterministic game of perfect information. Monte-Carlo Tree Search (MCTS) is an AI technique that has recently proved successful in the domain of deterministic games of perfect information. This paper studies the strengths and weaknesses of determiniz... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Reinforcement learning for the soccer dribbling task

    Publication Year: 2011, Page(s):95 - 101
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (880 KB) | HTML iconHTML

    We propose a reinforcement learning solution to the soccer dribbling task, a scenario in which a soccer agent has to go from the beginning to the end of a region keeping possession of the ball, as an adversary attempts to gain possession. While the adversary uses a stationary policy, the dribbler learns the best action to take at each decision point. After defining meaningful variables to represen... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Evolving multimodal networks for multitask games

    Publication Year: 2011, Page(s):102 - 109
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (860 KB) | HTML iconHTML

    Intelligent opponent behavior helps make video games interesting to human players. Evolutionary computation can discover such behavior, especially when the game consists of a single task. However, multitask domains, in which separate tasks within the domain each have their own dynamics and objectives, can be challenging for evolution. This paper proposes two methods for meeting this challenge by e... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • αβ-based play-outs in Monte-Carlo Tree Search

    Publication Year: 2011, Page(s):110 - 117
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (626 KB) | HTML iconHTML

    Monte-Carlo Tree Search (MCTS) is a recent paradigm for game-tree search, which gradually builds a game-tree in a best-first fashion based on the results of randomized simulation play-outs. The performance of such an approach is highly dependent on both the total number of simulation play-outs and their quality. The two metrics are, however, typically inversely correlated - improving the quality o... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.