Constructing Game Agents from Video of Human Behavior Export

@inproceedings{citeulike:5995780, abstract = {Developing computer game agents is often a lengthy and expensive undertaking. Detailed domain knowledge and decision-making procedures must be encoded into the agent to achieve realistic behavior. In this paper, we simplify this process by using the Icarus cognitive architecture to construct game agents. The system acquires structured, high fidelity methods for agents that utilize a vocabulary of concepts familiar to game experts. We demonstrate our approach by first acquiring behaviors for football agents from video footage of college football games, and then applying the agents in a football simulator.}, author = {Li, Nan and Stracuzzi, David J. and Cleveland, Gary and Konik, Tolga and Shapiro, Dan and Molineaux, Matt and Aha, David W. and Ali, Kamal}, booktitle = {Proceedings of the Fifth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE)}, citeulike-article-id = {5995780}, citeulike-linkout-0 = {http://www.public.asu.edu/~dstracuz/publications/icarus-aiide09/}, keywords = {ai, cooperative, crowd, formations, games, learning, steering, team, video\_as\_input}, month = {October}, posted-at = {2009-10-23 02:04:55}, priority = {2}, title = {Constructing Game Agents from Video of Human Behavior}, url = {http://www.public.asu.edu/~dstracuz/publications/icarus-aiide09/}, year = {2009} }

TY - CONF ID - citeulike:5995780 L3 - citeulike-article-id:5995780 N2 - Developing computer game agents is often a lengthy and expensive undertaking. Detailed domain knowledge and decision-making procedures must be encoded into the agent to achieve realistic behavior. In this paper, we simplify this process by using the Icarus cognitive architecture to construct game agents. The system acquires structured, high fidelity methods for agents that utilize a vocabulary of concepts familiar to game experts. We demonstrate our approach by first acquiring behaviors for football agents from video footage of college football games, and then applying the agents in a football simulator. TI - Constructing Game Agents from Video of Human Behavior T2 - Proceedings of the Fifth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE) KW - ai KW - cooperative KW - crowd KW - formations KW - games KW - learning KW - steering KW - team KW - video_as_input AU - Li, Nan AU - Stracuzzi, David AU - Cleveland, Gary AU - Konik, Tolga AU - Shapiro, Dan AU - Molineaux, Matt AU - Aha, David AU - Ali, Kamal PY - 2009/10// UR - http://www.public.asu.edu/~dstracuz/publications/icarus-aiide09/ ER -