ABSTRACT
This paper presents a novel approach to modeling a generic cognitive framework in game agents to provide tactical behavior generation as well as strategic decision making in modern multi-agent computer games. The core of our framework consists of two characterization concepts we term as the tactical and strategic personalities, embedded in each game agent. Tactical actions and strategic plans are generated according to the weights defined in their respective personalities. The personalities are constantly improved as the game proceeds by a learning process based on reinforcement learning. Also, the strategies selected at each level of the agents' command hierarchy affect the personalities and hence the decisions of other agents. The learning system improves performance of the game agents in combat and is decoupled from the action selection mechanism to ensure speed. The variability in tactical behavior and decentralized strategic decision making improves realism and increases entertainment value. Our framework is implemented in a real game scenario as an experiment and shown to outperform various scripted opponent team tactics and strategies, as well as one with a randomly varying strategy.
- Andrade, G., Ramalho, G., Santana, H., and Corruble, V. 2005. Automatic computer game balancing: A reinforcement learning approach. In Proceedings of the Autonomous Agents And Multi Agent Systems Conference (July), 1111, 1112. Google ScholarDigital Library
- Blizzard Entertainment, 2006. Warcraft III. Accessed April 12, 2006. Available via http://www.blizzard.com/war3/.Google Scholar
- Blizzard, 2006. Diablo ii. Accessed April 12, 2006. Available via http://www.blizzard.com/diablo2/.Google Scholar
- Blizzard, 2006. World of warcraft. Accessed April 12, 2006. Available via http://www.worldofwarcraft.com/.Google Scholar
- Buro, M., 2007. ORTS - A Free Software RTS Game Engine. Accessed March 20, 2007. Available via http://www.cs.ualberta.ca/mburo/orts/index.html.Google Scholar
- Charles, D., Kerr, A., McNeill, M., McAlister, M., Black, M., Kcklich, J., Moore, A., and Stringer, K. 2005. Player-centred game design: Player modeling and adaptive digital games. In Proceedings of the Digital Games Research Conference, 285,298.Google Scholar
- Christian J. Darken, G. H. P. 2006. Findin Cover in Dynamic Environments, first ed. Charles River Media, Hingham, Massachusetts.Google Scholar
- Co-op, S., 2006. Sven co-op. Accessed September 15, 2006. Available via http://www.svencoop.com/.Google Scholar
- Electronic Arts, 2006. Battlefield 2142. Accessed December 20, 2006. Available via http://battlefield.ea.com/battlefield/bf2142/.Google Scholar
- Exluna, Inc. 2002. Entropy 3.1 Technical Reference, January.Google Scholar
- Fedkiw, R., Stam, J., and Jensen, H. W. 2001. Visual simulation of smoke. In Proceedings of SIGGRAPH 2001, ACM Press / ACM SIGGRAPH, E. Fiume, Ed., Computer Graphics Proceedings, Annual Conference Series, ACM, 15--22. Google ScholarDigital Library
- Foka, A., and Trahanias, P. 2007. Real-time hierarchical POMDPs for autonomous robot navigation. In Proceedings of Robotics and Autonomous Systems, 561,571. Google ScholarDigital Library
- Geramifard, A., Chubak, P., and Bulitko, V. 2006. Biased cost pathfinding. In Proceedings of the Artificial Intelligence and Interactive Digital Entertainment conference, 112,114.Google Scholar
- Horswill, I., and Zubek, R. 1999. Robot architectures for believable game agents. In Proceedings of the 1999 AAAI Spring Symposium on Artificial Intelligence and Computer Games, AAAI Technical Report SS-99-02.Google Scholar
- Hunicke, R., and Chapman, V. 2004. AI for Dynamic Difficult Adjustment in Games. In Proceedings of the Challenges in Game AI Workshop, Nineteenth National Conference on Artificial Intelligence. Google ScholarDigital Library
- Hussain, T. S., and Vidaver, G. 2006. Flexible and purposeful npc behaviors using real-time genetic control. In Proceedings of The IEEE Congress on Evolutionary Computation (July), 785,792.Google Scholar
- Jobson, D. J., Rahman, Z., and Woodell, G. A. 1995. Retinex image processing: Improved fidelity to direct visual observation. In Proceedings of the IS&T Fourth Color Imaging Conference: Color Science, Systems, and Applications, vol. 4, 124--125.Google Scholar
- Kartch, D. 2000. Efficient Rendering and Compression for Full-Parallax Computer-Generated Holographic Stereograms. PhD thesis, Cornell University. Google ScholarDigital Library
- Khoo, A., and Dunham, G. 2002. Efficient, realistic npc control systems using behavior-based techniques. In AAAI Technical Report, 02--01.Google Scholar
- Landis, H., 2002. Global illumination in production. ACM SIGGRAPH 2002 Course #16 Notes, July.Google Scholar
- Levoy, M., Pulli, K., Curless, B., Rusinkiewicz, S., Koller, D., Pereira, L., Ginzton, M., Anderson, S., Davis, J., Ginsberg, J., Shade, J., and Fulk, D. 2000. The digital michelangelo project. In Proceedings of SIGGRAPH 2000, ACM Press / ACM SIGGRAPH, New York, K. Akeley, Ed., Computer Graphics Proceedings, Annual Conference Series, ACM, 131--144. Google ScholarDigital Library
- McDonald, D., Leung, A., Ferguson, W., and Hussain, T. 2006. An abstraction framework for cooperation among agents and people in a virtual world. In Proceedings of the Second Conference on Artificial Intelligence and Interactive Digital Entertainment (June).Google Scholar
- Michael E. Tipping, C. M. B. 1999. Probabilistic principal component analysis. Technical Report NCRG/97/010, Neural Computing Research Grou (September).Google Scholar
- NCsoft, 2006. Guild wars. Accessed April 12, 2006. Available via http://www.guildwars.com/.Google Scholar
- Oliehoek, F. 2005. Game Theory and AI: A unified Approach to Poker Games. Masters Thesis, 561,571.Google Scholar
- Orkin, J. 2004. Applying Goal-Oriented Action Planning to Games, first ed. Charles River Media, Hingham, Massachusetts.Google Scholar
- Orkin, J. 2004. Finite State Machines, first ed. Charles River Media, Hingham, Massachusetts.Google Scholar
- Orr, G., Schraudolph, N., and Cummins, F., 1999. Cs-449: Neural networks lecture notes. Accessed December 20, 2005. Available via http://www.willamette.edu/gorr/classes/cs449/intro.html.Google Scholar
- Park, S. W., Linsen, L., Kreylos, O., Owens, J. D., and Hamann, B. 2006. Discrete sibson interpolation. IEEE Transactions on Visualization and Computer Graphics 12, 2 (Mar./Apr.), 243--253. Google ScholarDigital Library
- Parke, F. I., and Waters, K. 1996. Computer Facial Animation. A. K. Peters. Google ScholarDigital Library
- Pellacini, F., Vidimče, K., Lefohn, A., Mohr, A., Leone, M., and Warren, J. 2005. Lpics: a hybrid hardware-accelerated relighting engine for computer cinematography. ACM Transactions on Graphics 24, 3 (Aug.), 464--470. Google ScholarDigital Library
- Remco Straatman, A. B., and van der Sterren, W. 2006. Dynamic Tactical Postion Evaluation, first ed. Charles River Media, Hingham, Massachusetts.Google Scholar
- Sailera, F., Buro, M., and Lanctot, M. 2007. Adversarial planning through strategy simulation. In Proceedings of the IEEE Symposium on Computational Intelligence and Games (April).Google Scholar
- Sako, Y., and Fujimura, K. 2000. Shape similarity by homotropic deformation. The Visual Computer 16, 1, 47--61.Google ScholarDigital Library
- Sierra, 2006. No one lives forever 2. Accessed April 12, 2006. Available via http://nolf.sierra.com/.Google Scholar
- Sierra, 2007. First encounter assault recon. Accessed December 23, 2007. Available via http://www.whatisfear.com/fear.html.Google Scholar
- Silver, D. 2005. Cooperative pathfinding. In Proceedings of the First Artificial Intelligence and Interactive Digital Entertainment conference, 117,122.Google ScholarDigital Library
- Spronck, P., Sprinkhuizen-Kuyper, I., and Postma, E. 2004. Difficulty Scaling of Game AI. In Proceedings of GAMEON 2004: 5th International Conference on Intelligent Games and Simulation, 33,37.Google Scholar
- Spronck, P., Ponsen, M., Sprinkhuizen-Kuyper, I., and Postma, E. 2006. Adaptive Game AI with Dynamic Scripting. Springer Netherlands, Netherlands.Google Scholar
- Spronck, P. 2005. A model for reliable adaptive game intelligence. In IJCAI-05 Workshop on Reasoning, Representation, and Learning in Computer Games, 95,100.Google Scholar
- Sutton, R. S., and Barto, A. G. 1998. Reinforcement Learning: An Introduction. The MIT Press, Cambridge, Massachusetts. Google ScholarDigital Library
- Sweetser, P. 2005. An emergent approach to game design. Ph.D Thesis. Available via http://www.itee.uq.edu.au/penny/publications.Google Scholar
- Tan, C. T., and Cheng, H. 2007. Personality-based Adaptation for Teamwork in Game Agents. In Proceedings of the Third Conference on Artificial Intelligence and Interactive Digital Entertainment, 37.Google Scholar
- Thue, D., and Bulitko, V. 2006. Modeling goal-directed players in digital games. In Proceedings of the Artificial Intelligence and Interactive Digital Entertainment conference, 285,298.Google Scholar
- Wallace, N. 2004. Hierarchical Planning in Dynamic Worlds, first ed. Charles River Media, Hingham, Massachusetts.Google Scholar
- White, C., and Brogan, D. 2006. The self organization of context for multi agent games. In Proceedings of 2nd Annual Conference on Artificial Intelligence in Interactive Digital Entertainment (June).Google Scholar
- Wikipedia, 2006. Game balance. Accessed December 20, 2006. Available via http://en.wikipedia.org/wiki/Gamebalance.Google Scholar
- Yannakakis, G. N., and Maragoudakis, M. 2005. Player modeling impact on players entertainment in computer games. In Springer-Verlag: Lecture Notes in Computer Science, 3538:74. Google ScholarDigital Library
- Yee, Y. L. H. 2000. Spatiotemporal sensistivity and visual attention for efficient rendering of dynamic environments. Master's thesis, Cornell University.Google Scholar
Index Terms
- A combined tactical and strategic hierarchical learning framework in multi-agent games
Recommendations
First-Person Shooter Game for Virtual Reality Headset with Advanced Multi-Agent Intelligent System
MM '16: Proceedings of the 24th ACM international conference on MultimediaWe present a multiplayer first-person shooter (FPS) game with advanced intelligent non-playable characters (NPC) under computer control. The game is specially adapted for playing in VR headset so the simulator sickness symptoms are significantly ...
Multi-agent learning in extensive games with complete information
AAMAS '03: Proceedings of the second international joint conference on Autonomous agents and multiagent systemsLearning in a multi-agent system is difficult because the learning environment jointly created by all learning agents is time-variant. This paper studies the model of multi-agent learning in complete-information extensive games (CEGs). We provide two ...
Comments