Summary: Towards a Bayesian Model for Keyhole Plan Recognition in
Large Domains 1
D.W. Albrecht, I. Zukerman, A.E. Nicholson, and A. Bud
Department of Computer Science, Monash University
Clayton, VICTORIA 3168, Australia
phone: +61 3 99055225 fax: +61 3 99055146
fdwa, ingrid, annn, email@example.com
We present an approach to keyhole plan recognition which uses a Dynamic Be
lief Network to represent features of the domain that are needed to identify users'
plans and goals. The structure of this network was determined from analysis of
the domain. The conditional probability distributions are learned during a train
ing phase, which dynamically builds these probabilities from observations of user
behaviour. This approach allows the use of incomplete, sparse and noisy data both
during training and testing. We present experimental results of the application of
our system to a MultiUser Dungeon adventure game with thousands of possible
actions and positions. These results show a high degree of predictive accuracy and
indicate that this approach will work in other domains with similar features.
Keywords: Plan recognition, Bayesian networks, dynamic belief networks, large domains.