This is the final list of special sessions which will be included at CIG 2012.
Prospective authors are invited to contribute their papers to Special Session on Computational Creativity in Games. All papers have to be submitted electronically following the same process and formatting instructions as for regular papers, but choosing the correspondent special session trrack. See the submission section for more details.
All the accepted papers will be published in the proceedings of the conference.
Please contact the respective organizers or the special sessions chair if you have any question about them.
Computational Creativity in Games
Computational Intelligence (CI) techniques, including evolutionary computing, particle swarm optimization, ant colony optimization, differential evolution, neural networks, trajectory-based optimization methods, machine learning, constraint programming methods, and also (multi-)agent systems, data mining, influence mapping, ...,etc, have shown to be effective for search and optimization problems and have gained several promising results and becomes an important tool in Computational Creativity, such as in music, visual art, literature, architecture, and industrial design.
It is also well known (and globally accepted) that game programming requires a high level of creativity in a number of areas such as music composition, 2D/3D modelling, game narrative, game level/maps creation, player modelling, game AI, emergent behavior generation, and procedural content generation in general among others. In this context, computational intelligence techniques can play an important role in Game Creativity.
The aim of this special session is to reflect the most recent advances of Computational Creativity in Games, with the goal to enhance autonomous creative systems as well as human creativity in any area of the development of (video)games. This session will allow researchers to share experiences and present their new ways for taking advantage of CI techniques in Games Creativity.
Topics of interest include, but are not limited to, CI technologies applied to games in the following aspects:
- Creativity in generation of music, visual art, architecture and design
- Creativity in algorithmic design
- Creativity in optimization
- Creativity in development of hardware and software for games
- Creativity in evaluation methodologies
- Creativity in assistance of human creativity
- Creativity in computational aesthetics
- Creativity in emotion/emotional response
- Creativity in human-machine creativity
- Creativity in emergent behaviour
- Creativity in 2D/3D modelling
- Creativity in social games
- Creativity in any genre of games including multiplayer games
- Creativity in the automatic content generation for games (i.e., procedural content generation, track generation in racing games, map/level creation, dynamic terrain...)
- Creativity in board games
- Creativity in Opponent modelling
- Creativity in Player modelling/prediction
- Creativity in representation issues
- Creativity in mate behavior in games (e.g., squad coordination in first person shooter games or in real time strategy games).
- Creativity in motion planning
- Creativity in combat reasoning
organizers: Carlos Cotta and Antonio J. Fernández Leiva
Monte Carlo Tree Search for Games
Monte Carlo Tree Search (MCTS) is a novel tree search algorithm that has led to recent breakthroughs in computer Go and other games. MCTS, unlike classical tree search algorithms, is any-time and does not necessarily require a state value function. These attributes make MCTS a promising candidate for games in which traditional tree search algorithms tend to fail. MCTS has been applied successfully to a wide variety of games, including puzzles, board games, card games and real-time video games, and has produced world champion AI players for a number of difficult games. More recently, MCTS has also been proposed as a method for automated level and game design.
The aim of this special session is to highlight these advances and to bring together high quality publications concerning the study, analysis and application of MCTS with respect to games.
Topics of interest include, but are not limited to:
- MCTS for intelligent move planning
- MCTS for opponent modelling
- Learning in MCTS
- Hybrid MCTS algorithms
- MCTS for real-time (video) games
- MCTS for continuous domains
- MCTS for open-ended (infinite) domains
- MCTS for nondeterministic / hidden information games
- MCTS for social (multiplayer / euro / bidding / gambling) games
- MCTS for solitaire puzzle design and solving
- MCTS for game, content and level design
- Enhancements and variations of MCTS
organizers: Philipp Rohlfshagen, Edward Powley and Cameron Browne
Computational Intelligence in Racing Games
Modern racing games provide vivid representations of the game
environment and very realistic physics engines that accurately model
the dynamics of racing cars. At the same time, they also need a very
sophisticated and believable AI to meet the increasingly high
expectations of players.
Computational intelligence offers a range of interesting new ideas and techniques for racing game developers. So far, both published academic research, the entrants of the recurring simulated car racing competitions, and some notable applications in high-end commercial games have shown that computational intelligence techniques can successfully be used in the racing games domain.
The aim of this special session is to bring together leading researchers in this field and gather the best new research, the most innovative ideas, and the future directions within this research area.
Topics of interest include, but are not limited to, the following:
- On-line Learning in Racing Games
- Player/Opponent Modeling in Racing Games
- CI-based Gameplay for Racing Games
- Procedural Game Content Generation in Racing Games
- Player Satisfaction and Experience Modelling and Optimization in Racing Games
- Novel CI Platforms & Benchmarks Based on Racing Games
- CI Applications in Racing Games
organizers: Pier Luca Lanzi, Luigi Cardamone and Daniele Loiacono
Game Data Mining
Since the first computer game, the behavior of the players has been registered, and responses to these behaviors calculated in real-time. In recent years extracting logs of player behavior, game telemetry, has enabled game researchers and game developers to adopt behavioral analysis at hitherto unprecedented levels of resolution. In addition, contemporary commercial computer games provide an ideal environment for the study of human behavior. Being closed worlds of considerable complexity, games allow for investigating behavior patterns, decision making, and preference modeling.
Advances in these areas serve both to improve our understanding of players and learning in games, and improving game design and game play. Game data mining has a high potential as an enabler of future business, but requires for recording and storage of large amounts of telemetry data as well as efficient methods for the processing and analysis of large scale data sets.
Topics of interest for this special session include, but are not limited to, the following:
- In-game telemetry data collection
- Practical applications of game mining
- Efficient representation and visualization of in-game data
- Algorithms for (large scale) game mining
- User modeling based on behavioral telemetry data
- Player evaluation and playability testing
- Computational intelligence for behavior pattern analysis
- Empirical studies based on telemetry data
- Future directions for in-game data mining
organizers: Christian Thurau, Anders Drachen, Alessandro Canossa, Christian Bauckhage and Kristian Kersting
Version 2.5 - September, 2012