2006 IEEE Symposium on Computational Intelligence and Games

22-24 May 2006

Filter Results

Displaying Results 1 - 25 of 48
  • [Front cover]

    Publication Year: 2006, Page(s): C1
    Request permission for commercial reuse | PDF file iconPDF (470 KB)
    Freely Available from IEEE
  • [Breaker page]

    Publication Year: 2006, Page(s): 1
    Request permission for commercial reuse | PDF file iconPDF (22 KB)
    Freely Available from IEEE
  • [Breaker page]

    Publication Year: 2006, Page(s): 2
    Request permission for commercial reuse | PDF file iconPDF (46 KB)
    Freely Available from IEEE
  • Table of contents

    Publication Year: 2006, Page(s):3 - 4
    Request permission for commercial reuse | PDF file iconPDF (219 KB)
    Freely Available from IEEE
  • [Commentary]

    Publication Year: 2006, Page(s): 5
    Request permission for commercial reuse | PDF file iconPDF (53 KB) | HTML iconHTML
    Freely Available from IEEE
  • [Breaker page]

    Publication Year: 2006, Page(s): 6
    Request permission for commercial reuse | PDF file iconPDF (61 KB)
    Freely Available from IEEE
  • Contributor Listings

    Publication Year: 2006
    Request permission for commercial reuse | PDF file iconPDF (112 KB)
    Freely Available from IEEE
  • [Society related material]

    Publication Year: 2006, Page(s): 9
    Request permission for commercial reuse | PDF file iconPDF (138 KB)
    Freely Available from IEEE
  • [Breaker page]

    Publication Year: 2006, Page(s): 11
    Request permission for commercial reuse | PDF file iconPDF (12 KB)
    Freely Available from IEEE
  • ChessBrain II - A Hierarchical Infrastructure for Distributed Inhomogeneous Speed-Critical Computation

    Publication Year: 2006, Page(s):13 - 18
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1844 KB) | HTML iconHTML

    The ChessBrain project holds an official Guinness World Record for the largest number of computers used to play one single game of chess. In this paper, we cover the latest developments in the ChessBrain project, which now includes the use of a highly scalable, hierarchically distributed communications model View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Grid-Robot Drivers: an Evolutionary Multi-agent Virtual Robotics Task

    Publication Year: 2006, Page(s):19 - 26
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2674 KB) | HTML iconHTML

    Beginning with artificial ants and including such tasks as Tartarus, software agents that are situated on a grid have been a staple of evolutionary computation. This manuscript introduces a grid-robot problem in which the agents simulate single or multiple drivers on a two-lane interstate freeway that may have obstructions. The drivers are represented as if-skip-action lists, a linear genetic prog... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optimizations of data structures, heuristics and algorithms for path-finding on maps

    Publication Year: 2006, Page(s):27 - 33
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1328 KB) | HTML iconHTML

    This paper presents some optimizations of A* and IDA* for pathfinding on maps. The best optimal pathfinder we present can be up to seven times faster than the commonly used pathfinders as shown by experimental results. We also present algorithms based on IDA* that can be even faster at the cost of optimality. The optimizations concern the data structures used for the open nodes, the admissible heu... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Decentralized Decision Making in the Game of Tic-tac-toe

    Publication Year: 2006, Page(s):34 - 38
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1042 KB) | HTML iconHTML

    Traditionally, the game of Tic-tac-toe is a pencil and paper game played by two people who take turn to place their pieces on a 3times3 grid with the objective of being the first player to fill a horizontal, vertical, or diagonal row with their pieces. What if instead of having one person playing against another, one person plays against a team of nine players, each of whom is responsible for one ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Integration and Evaluation of Exploration-Based Learning in Games

    Publication Year: 2006, Page(s):39 - 44
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1873 KB) | HTML iconHTML

    Video and computer games provide a rich platform for testing adaptive decision systems such as value-based reinforcement learning and neuroevolution. However, integrating such systems into the game environment and evaluating their performance in it is time and labor intensive. In this paper, an approach is developed for using general integration and evaluation software to alleviate these problems.... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Coevolutionary Model for The Virus Game

    Publication Year: 2006, Page(s):45 - 51
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2582 KB) | HTML iconHTML

    In this paper, coevolution is used to evolve artificial neural networks (ANN) which evaluate board positions of a two player zero-sum game (the virus game). The coevolved neural networks play at a level that beats a group of strong hand-crafted AI players. We investigate the performance of coevolution starting from random initial weights and starting with weights that are tuned by gradient based a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Temporal Difference Learning Versus Co-Evolution for Acquiring Othello Position Evaluation

    Publication Year: 2006, Page(s):52 - 59
    Cited by:  Papers (26)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3132 KB) | HTML iconHTML

    This paper compares the use of temporal difference learning (TDL) versus co-evolutionary learning (CEL) for acquiring position evaluation functions for the game of Othello. The paper provides important insights into the strengths and weaknesses of each approach. The main findings are that for Othello, TDL learns much faster than CEL, but that properly tuned CEL can learn better playing strategies.... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The Effect of Using Match History on the Evolution of RoboCup Soccer Team Strategies

    Publication Year: 2006, Page(s):60 - 66
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2301 KB) | HTML iconHTML

    In this paper we improve the performance of an evolutionary method for obtaining team strategies in simulated robot soccer. In the previous method each team strategy was evaluated based on the goals and the goals against of a single game. It is possible for a good team strategy to be eliminated from the population in the evolutionary method as there is a high degree of uncertainty in the simulated... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Training Bao Game-Playing Agents using Coevolutionary Particle Swarm Optimization

    Publication Year: 2006, Page(s):67 - 74
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1528 KB) | HTML iconHTML

    Bao, an African board game of the Mancala family, is a complex two-player game with a very large search space and complex rule set. The success of game tree approaches to create game-playing agents rests heavily on the usually handcrafted, static evaluation function. One of the first steps towards using a game tree is to design an appropriate, efficient evaluation function. This paper investigates... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Towards the Co-Evolution of Influence Map Tree Based Strategy Game Players

    Publication Year: 2006, Page(s):75 - 82
    Cited by:  Papers (19)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (6053 KB) | HTML iconHTML

    We investigate the use of genetic algorithms to play real-time computer strategy games. To overcome the knowledge acquisition bottleneck found in using traditional expert systems, scripts, or decision trees we use genetic algorithms to evolve game players. The spatial decision makers in our game players use influence maps as a basic building block from which they construct and evolve trees contain... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Player for Tactical Air Strike Games Using Evolutionary Computation

    Publication Year: 2006, Page(s):83 - 89
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2988 KB) | HTML iconHTML

    This paper discusses the use of evolutionary computation for an automated player of a real-time strategic tactics game in which assets are assigned to targets and threats belonging to the opposing team. Strategy games such as this are essentially a series of asset allocation problems to which evolutionary algorithms are particularly adept. This game contains a significant coupling affect between t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Exploiting Sensor Symmetries in Example-based Training for Intelligent Agents

    Publication Year: 2006, Page(s):90 - 97
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3476 KB) | HTML iconHTML

    Intelligent agents in games and simulators often operate in environments subject to symmetric transformations that produce new but equally legitimate environments, such as reflections or rotations of maps. That fact suggests two hypotheses of interest for machine-learning approaches to creating intelligent agents for use in such environments. First, that exploiting symmetric transformations can br... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Using Wearable Sensors for Real-Time Recognition Tasks in Games of Martial Arts - An Initial Experiment

    Publication Year: 2006, Page(s):98 - 102
    Cited by:  Papers (18)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (4199 KB) | HTML iconHTML

    Beside their stunning graphics, modern entertainment systems feature ever-higher levels of immersive user-interaction. Today, this is mostly achieved by virtual (VR) and augmented reality (AK) setups. On top of these, we envision to add ambient intelligence and context awareness to gaming applications in general and games of martial arts in particular. To this end, we conducted an initial experime... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Self-Adapting Payoff Matrices in Repeated Interactions

    Publication Year: 2006, Page(s):103 - 110
    Cited by:  Papers (11)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1633 KB) | HTML iconHTML

    Traditional iterated prisoner's dilemma (IPD) assumed a fixed payoff matrix for all players, which may not be realistic because not all players are the same in the real-world. This paper introduces a novel co-evolutionary framework where each strategy has its own self-adaptive payoff matrix. This framework is generic to any simultaneous two-player repeated encounter game. Here, each strategy has a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Training Function Stacks to play the Iterated Prisoner's Dilemma

    Publication Year: 2006, Page(s):111 - 118
    Cited by:  Papers (15)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3275 KB) | HTML iconHTML

    Cartesian genetic programming uses a directed acyclic graph structure rather than a tree structure for its representation of evolvable programs or formulas. In this paper a derivative of Cartesian genetic programming called a function stack is introduced and trained to play the iterated prisoner's dilemma with an evolutionary algorithm. Function stacks differ from Cartesian genetic programming in ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optimization Problem Solving using Predator/Prey Games and Cultural Algorithms

    Publication Year: 2006, Page(s):119 - 125
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (4693 KB) | HTML iconHTML

    This paper looks at optimization problem solving from the standpoint of a predator/prey paradigm. In that paradigm, knowledge sources (or decision makers) control the placement of individuals onto a multi-dimensional landscape. Their score is the sum of the resources collected by each of the individuals that they control. While simple, this game has many of the properties present in much more comp... View full abstract»

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