Research in Multi-Agent Systems offers promising technologies to implement non-playing characters embodying more realistic cognitive models. However, the technologies used in today's game engines and multi-agent platforms are not readily compatible due to some differences in their major concerns. For example, where game engines focus on real-time aspects that prioritize efficiency and central control, multi-agent platforms privilege agent autonomy instead. And while multi-agent platforms typically offer sophisticated communication capabilities, these may not be usable, or even appropriate, when the agents are coupled to a game. So, although increased autonomy and intelligence may offer benefits for a more compelling game play—and may even be essential for serious games—it is not clear whether current multi agent platforms offer the means that are needed to accomplish this. Indeed, when current approaches to game design are used to incorporate state of the art Multi-Agent System technology, the autonomy and intelligence of the agents might even be seen more as a hindrance than an asset. A very similar argument can be given for approaches based on agent-based (social) simulations.
In this workshop we want to bring people together that address the particular challenges of using agent technology for games and simulations.
Just like last year the workshop will have three main themes:
Of course we also welcome any papers about experiences on the use of agents in games and simulations. This can be applications where agents are replacing persons in training situations, where agents function as virtual tutors or in any other way enhance the game play. We also would like to invite explicitly contributions that describe the use of agents with rich cognitive models in simulations. Both success as well as "failures" are welcome as they both can help us better understand what are the key issues in combining agents with game and simulation engines.
To have look on what kind of papers were presented last year have a look at the website of AGS09. The proceedings of that workshop are available from Springer LNAI-5920 Agents for Games and Simulations.
Submissions should be submitted through the EasyChair system website for AGS 2010
either in PostScript format or in PDF format.
The deadline for receipt of submissions is February, 02, 2010. Papers received after this date will not be reviewed.
The proceedings of the workshop will be published as an LNAI volume with Springer if quality is as high as last year.
Frank Dignum, Utrecht University, The Netherlands, email@example.com
Jeffrey M. Bradshaw, IHMC, Florida, USA, firstname.lastname@example.org
Jeff Orkin, MIT, USA, email@example.com
Annerieke Heuvelink, TNO, The Netherlands, firstname.lastname@example.org