Tutorial 1: CULTURAL ALGORITHMS: Incorporating Social Intelligence Into Virtual Worlds

Bob Reynolds (Wayne State University)

The intended audience will be those students and practitioners who are interested in adding social intelligence into virtual worlds. Attendees will be provided with concepts and software tools that will illustrate how to design in cultural knowledge and social behavior into virtual worlds. Currently intelligence within virtual worlds is often at the level of individual agents, This tutorial is unique in that it demonstrates the ease with which social intelligence can be integrated into a system and the resultant advantages of doing so in terms of virtual world performance (read more).

Tutorial 2: Automating the Analysis of Evolved Agents

Daniel Ashlock (Univ. of Guelph)

One of the down sides to evolving or training a game strategy on a series of examples is that the resulting strategy often defies simple analysis. This tutorial introduces a number of related helpful techniques for understanding artificial agents or strategies produced

via computational intelligence techniques. The key tool is the development of meaningful numerical signatures for the behavior of agents that can then be clustered, classified, or visualized. These techniques include: (read more)

Tutorial 3: Experience-Driven Procedural Content Generation

Georgios N. Yannakakis and Julian Togelius (IT University of Copenhagen)

We will talk about how to combine procedural content generation (PCG) and player modelling using computational intelligence techniques. In other words, we will talk about how to model what the player does and what the player wants (using for example neural networks) and how to create new game elements (levels, maps, trees, characters etc) using for example evolutionary computation. But we will not only talk about how to do it, but also why. We believe this combination of techniques is the key to creating games that have almost infinite replay value, that adapt to particular players’ needs and competence, and can be significantly cheaper to produce than todays AAA games. Also, it makes for some interesting research problems.

Tutorial 4:  Experimentation in CI-Affected Games Research

Mike Preuss (Dortmund University)

Experimentation (sometimes also called empiricism) is an important factor in domains with strong real-world influences. Many constraints and interactions within algorithmic factors and other game components and a final objective (player satisfaction) that is difficult to quantify make it hard to assess suggested solutions. The non-determinism introduced by many CI-based methods can be an asset but adds another source of uncertainty that requires a statistical approach. However, this noise factor cannot be completely get rid off here as long as there are humans actually playing the resulting games. We summarize the current state of research concerning this human factor and the currently employed methods to handle it (read more).

Leave a Reply