Markov decisions processes (MDPs) are becoming increasing popular as models of decision theoretic planning. While traditional dynamic programming methods perform well for problems with small state spaces, structured methods are needed for large problems. We propose and examine a value iteration algorithm for MDPs that uses algebraic decision diagrams(ADDs) to represent value functions and policies. An MDP is represented using Bayesian networks and ADDs and dynamic programming is applied directly to these ADDs. We demonstrate our method on large MDPs (up to 63 million states) and show that significant gains can be had when compared to tree-structured representations (with up to a thirty-fold reduction in the number of nodes required to represent optimal value functions).

This paper extends previous work with network fragments and situation-specific network construction. We formally define the asymmetry network, an alternative representation for a conditional probability table. We also present an object-oriented representation for partially specified asymmetry networks. We show that the representation is parsimonious. We define an algebra for the elements of the representation that allows us to 'factor' any CPT and to soundly combine the partially specified asymmetry networks.

This paper describes stochastic search approaches, including a new stochastic algorithm and an adaptive mutation operator, for learning Bayesian networks from incomplete data. This problem is characterized by a huge solution space with a highly multimodal landscape. State-of-the-art approaches all involve using deterministic approaches such as the expectation-maximization algorithm. These approaches are guaranteed to find local maxima, but do not explore the landscape for other modes. Our approach evolves structure and the missing data. We compare our stochastic algorithms and show they all produce accurate results.

In this paper, we empirically evaluate algorithms for learning four types of Bayesian network (BN) classifiers - Naive-Bayes, tree augmented Naive-Bayes, BN augmented Naive-Bayes and general BNs, where the latter two are learned using two variants of a conditional-independence (CI) based BN-learning algorithm. Experimental results show the obtained classifiers, learned using the CI based algorithms, are competitive with (or superior to) the best known classifiers, based on both Bayesian networks and other formalisms; and that the computational time for learning and using these classifiers is relatively small. Moreover, these results also suggest a way to learn yet more effective classifiers; we demonstrate empirically that this new algorithm does work as expected. Collectively, these results argue that BN classifiers deserve more attention in machine learning and data mining communities.

We introduce utility-directed procedures for mediating the flow of potentially distracting alerts and communications to computer users. We present models and inference procedures that balance the context-sensitive costs of deferring alerts with the cost of interruption. We describe the challenge of reasoning about such costs under uncertainty via an analysis of user activity and the content of notifications. After introducing principles of attention-sensitive alerting, we focus on the problem of guiding alerts about email messages. We dwell on the problem of inferring the expected criticality of email and discuss work on the Priorities system, centering on prioritizing email by criticality and modulating the communication of notifications to users about the presence and nature of incoming email.

The clique tree algorithm is the standard method for doing inference in Bayesian networks. It works by manipulating clique potentials - distributions over the variables in a clique. While this approach works well for many networks, it is limited by the need to maintain an exact representation of the clique potentials. This paper presents a new unified approach that combines approximate inference and the clique tree algorithm, thereby circumventing this limitation. Many known approximate inference algorithms can be viewed as instances of this approach. The algorithm essentially does clique tree propagation, using approximate inference to estimate the densities in each clique. In many settings, the computation of the approximate clique potential can be done easily using statistical importance sampling. Iterations are used to gradually improve the quality of the estimation.

Poker is ideal for testing automated reasoning under uncertainty. It introduces uncertainty both by physical randomization and by incomplete information about opponents hands.Another source OF uncertainty IS the limited information available TO construct psychological models OF opponents, their tendencies TO bluff, play conservatively, reveal weakness, etc. AND the relation BETWEEN their hand strengths AND betting behaviour. ALL OF these uncertainties must be assessed accurately AND combined effectively FOR ANY reasonable LEVEL OF skill IN the game TO be achieved, since good decision making IS highly sensitive TO those tasks.We describe our Bayesian Poker Program(BPP), which uses a Bayesian network TO model the programs poker hand, the opponents hand AND the opponents playing behaviour conditioned upon the hand, and betting curves which govern play given a probability of winning. The history of play with opponents is used to improve BPPs understanding OF their behaviour.We compare BPP experimentally WITH : a simple RULE - based system; a program which depends exclusively ON hand probabilities(i.e., without opponent modeling); AND WITH human players.BPP has shown itself TO be an effective player against ALL these opponents, barring the better humans.We also sketch out SOME likely ways OF improving play.

One of the most useful sensitivity analysis techniques of decision analysis is the computation of value of information (or clairvoyance), the difference in value obtained by changing the decisions by which some of the uncertainties are observed. In this paper, some simple but powerful extensions to previous algorithms are introduced which allow an efficient value of information calculation on the rooted cluster tree (or strong junction tree) used to solve the original decision problem.

Graphical models based on conditional independence support concise encodings of the subjective belief of a single agent. A natural question is whether the consensus belief of a group of agents can be represented with equal parsimony. We prove, under relatively mild assumptions, that even if everyone agrees on a common graph topology, no method of combining beliefs can maintain that structure. Even weaker conditions rule out local aggregation within conditional probability tables. On a more positive note, we show that if probabilities are combined with the logarithmic opinion pool (LogOP), then commonly held Markov independencies are maintained. This suggests a straightforward procedure for constructing a consensus Markov network. We describe an algorithm for computing the LogOP with time complexity comparable to that of exact Bayesian inference.

In this paper, we analyze the relationship between probability and Spohn's theory for representation of uncertain beliefs. Using the intuitive idea that the more probable a proposition is, the more believable it is, we study transformations from probability to Sphonian disbelief and vice-versa. The transformations described in this paper are different from those described in the literature. In particular, the former satisfies the principles of ordinal congruence while the latter does not. Such transformations between probability and Spohn's calculi can contribute to (1) a clarification of the semantics of nonprobabilistic degree of uncertain belief, and (2) to a construction of a decision theory for such calculi. In practice, the transformations will allow a meaningful combination of more than one calculus in different stages of using an expert system such as knowledge acquisition, inference, and interpretation of results.