This is the Second AAMAS Workshop on Cognitive Agents and Virtual Environments (CAVE) where the main issue has been to incorporate elements of agent technology in games and similar virtual environments such as 3D training and educational applications to create more flexible and realistic game play. This workshop builds upon previous AAMAS workshops (including AGS 2009/10, EduMAS 2009/10, AEGS 2011, MASEIE 2011 and CAVE 2012). Although some of the technical issues have been overcome and middleware (such as Pogamut, EIS and CIGA) has been developed to connect agent platforms to games like Unreal Tournament there are a number of fundamental challenges both on the technical as well as on conceptual and design level.
We intend to bring people working on virtual characters together with those working on agent platforms and languages and cognitive architectures. All three communities have important parts of solutions for creating agents for games and similar applications, but very little is currently being done to combine these solutions. Thus the workshop will encourage all submissions that connect the different communities and show the benefits from this combination.
There is a wide range of activity within the agent community considering various aspects of multi-agent systems, both theoretical as well as practical. This includes communication, team work, coordination and cooperation of agents. We want to explore how these results might be used in the context of games and other virtual applications that require interaction with real users and perhaps identify any additional requirements that should be imposed for these contexts. In particular, we seek to better understand the constraints imposed when agents are used in virtual learning environments and serious games and how the balance between learning, motivation and enjoyment can be achieved. To gain this understanding we also want to explore similarities between solutions developed within the agent community with those used by people studying cognitive architectures.
Finally, we would like to promote the testing and evaluation of suitable frameworks such that it will be clear which works best for the various types of game or application of gaming. To this end, creation of a testbed or environment for developing and evaluating games and simulations with agents will be explored at the workshop.
The topics of the workshop include but are not limited to:
• Methodologies for designing agent-based game environments
• Real-time reactive behaviour
• Balancing reactive and pro-active behaviour
• Cognitive approaches to agents for real-time systems (RTS) and games
• BDI-based agents for RTS and games
• Cognitive architectures used in the context of RTS and games
• Intelligent Virtual Agents (IVA)
• Spatial and Cognitive maps for games
• Ontologies for RTS and games
• Episodic memory for agents in games and RTS
• Interfacing agent platforms and cognitive architectures to real-time systems and games
• Design of Level of Detail of agent-gaming interfaces
• Scalability of agent technology and cognitive architectures
• Integrating agent architectures, cognitive architectures and IVA architectures
• Gaming middleware
• Approaches and methods for evaluating the agent platforms for RTS and games
• Benchmarks and test beds for evaluating agent technology for games
• Programmability of complex systems of agents interfaced with RTS and games
• Development and Design tools for engineering agents for RTS and games
• Teamwork approaches for agents in RTS and games
• Management and achievement of pedagogical goals and shared human/agent goals in the context of an educational or serious game
• Communication and coordination approaches for multi-agent systems for RTS and games
We welcome both theoretical papers that indicate how the theory can be used in practice as well as practical and empirical papers that provide solutions for theoretical issues. We also welcome in particular any papers that discuss experiences and lessons learned related to the application of agent technology in real-time systems and games. Both successes and "failures" are welcome as they both can help us to better understand the key issues in combining agents with real-time systems and games.
To have look on what kind of papers were presented last years have a look at the website of AGS09, AGS10, AEGS11 and CAVE 2012. The proceedings of those workshops are available from Springer LNAI-5920, LNAI-6525 and forthcoming.
Submissions should be submitted through the EasyChair system website for CAVE 2013
in PDF format.
The deadline for receipt of submissions is February 6, 2013. 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.
1. Ruth Aylett, Heriot-Watt University (UK)
2. Martin Beer, Sheffield Hallam University (UK)
3. Cyril Brom, Charles University (Czech Republic)
4. Andre Campos, UFRN (Brazil)
5. Yves Demazeau, CNRS - Laboratoire LIG (France)
6. Frank Dignum, Utrecht University (NL)
7. Hiromitsu Hattori, Kyoto University (Japan)
8. Koen Hindriks, Delft University of Technology (NL)
9. Stefan Kopp, University of Bielefeld (Germany)
10. Joost Van Oijen, Utrecht University (NL)
11. Jeff Orkin, MIT (USA)
12. David Pynadath, ICT, University of Southern California (USA)
13. Deborah Richards, Macquarie University (Australia)
14. Avi Rosenfeld, Jerusalem College of Technology (JCT) (Israel)
15. Ilias Sakellariou, University of Macedonia (Macedonia)
16. David Sarne, Bar-Ilan University (Israel)
17. Barry Silverman, University of Pennsylvania (USA)
18. Demosthenes Stamatis, Alexander TEI of Thessaloniki (Greece)
19. Ioanna Stamatopoulou, CITY College, University of Sheffield (UK)
20. Katia Sycara, Carnegie Mellon University (USA)
21. Janneke van der Zwaan, Delft University of Technology (NL)