Despite its ubiquitous presence, very little is known about the odds of winning the simple card game of Klondike Solitaire. The main goal of this paper is to investigate the use of probabilistic planning to shed light on this issue. Unfortunatley, most probabilistic planning techniques are not well suited for Klondike due to the difficulties of representing the domain in standard planning languages and the complexity of the required search. Klondike thus serves as an interesting addition to the complement of probabilistic planning domains. In this paper, we study Klondike using several sampling-based planning approaches including UCT, hindsight optimization, and sparse sampling, and establish lower bounds on their performance. We also introduce novel combinations of these approaches and evaluate them in Klondike. We provide a theoretical bound on the sample complexity of a method that naturally combines sparse sampling and UCT. Our results demonstrate that there is a policy that within tight confidence intervals wins over 35% of Klondike games. This result is the first reported lower bound of an optimal Klondike policy.

Distributed POMDPs provide an expressive framework for modeling multiagent collaboration problems, but NEXP-Complete complexity hinders their scalability and application in real-world domains. This paper introduces a subclass of distributed POMDPs, and TREMOR, an algorithm to solve such distributed POMDPs. The primary novelty of TREMOR is that agents plan individually with a single agent POMDP solver and use social model shaping to implicitly coordinate with other agents. Experiments demonstrate that TREMOR can provide solutions orders of magnitude faster than existing algorithms while achieving comparable, or even superior, solution quality.

Nowadays many urban areas have been equipped with networks of surveillance cameras, which can be used for automatic localization and tracking of people. However, given the large resource demands of imaging sensors in terms of bandwidth and computing power, processing the image streams of all cameras simultaneously might not be feasible. In this paper, we consider the problem of dynamical sensor selection based on user-defined objectives, such as maximizing coverage or improved localization uncertainty.  We propose a decision-theoretic approach modeled as a POMDP, which selects k sensors to consider in the next time frame, incorporating all observations made in the past. We show how, by changing the POMDP's reward function, we can change the system's behavior in a straightforward manner, fulfilling the user's chosen objective. We successfully apply our techniques to a network of 10 cameras.

We propose an online algorithm for planning under uncertainty in multi-agent settings modeled as DEC-POMDPs. The algorithm helps overcome the high computational complexity of solving such problems off-line. The key challenge is to produce coordinated behavior using little or no communication. When communication is allowed but constrained, the challenge is to produce high value with minimal communication. The algorithm addresses these challenges by communicating only when history inconsistency is detected, allowing communication to be postponed if necessary. Moreover, it bounds the memory usage at each step and can be applied to problems with arbitrary horizons. The experimental results confirm that the algorithm can solve problems that are too large for the best existing off-line planning algorithms and it outperforms the best online method, producing higher value with much less communication in most cases.

We consider the task of opportunistic channel access in a primary system composed of independent Gilbert-Elliot channels where the secondary (or opportunistic) user does not dispose of a priori information regarding the statistical characteristics of the system. It is shown that this problem may be cast into the framework of model-based learning in a specific class of Partially Observed Markov Decision Processes (POMDPs) for which we introduce an algorithm aimed at striking an optimal tradeoff between the exploration (or estimation) and exploitation requirements. We provide finite horizon regret bounds for this algorithm as well as a numerical evaluation of its performance in the single channel model as well as in the case of stochastically identical channels.

Many real-world decision making tasks require us to choose among several expensive observations. In a sensor network, for example, it is important to select the subset of sensors that is expected to provide the strongest reduction in uncertainty. In medical decision making tasks, one needs to select which tests to administer before deciding on the most effective treatment. It has been general practice to use heuristic-guided procedures for selecting observations. In this paper, we present the first efficient optimal algorithms for selecting observations for a class of probabilistic graphical models. For example, our algorithms allow to optimally label hidden variables in Hidden Markov Models (HMMs). We provide results for both selecting the optimal subset of observations, and for obtaining an optimal conditional observation plan. Furthermore we prove a surprising result: In most graphical models tasks, if one designs an efficient algorithm for chain graphs, such as HMMs, this procedure can be generalized to polytree graphical models. We prove that the optimizing value of information is $NP^{PP}$-hard even for polytrees. It also follows from our results that just computing decision theoretic value of information objective functions, which are commonly used in practice, is a #P-complete problem even on Naive Bayes models (a simple special case of polytrees). In addition, we consider several extensions, such as using our algorithms for scheduling observation selection for multiple sensors. We demonstrate the effectiveness of our approach on several real-world datasets, including a prototype sensor network deployment for energy conservation in buildings.

We present two algorithms for learning the structure of a Markov network from data: GSMN* and GSIMN. Both algorithms use statistical independence tests to infer the structure by successively constraining the set of structures consistent with the results of these tests. Until very recently, algorithms for structure learning were based on maximum likelihood estimation, which has been proved to be NP-hard for Markov networks due to the difficulty of estimating the parameters of the network, needed for the computation of the data likelihood. The independence-based approach does not require the computation of the likelihood, and thus both GSMN* and GSIMN can compute the structure efficiently (as shown in our experiments). GSMN* is an adaptation of the Grow-Shrink algorithm of Margaritis and Thrun for learning the structure of Bayesian networks. GSIMN extends GSMN* by additionally exploiting Pearl's well-known properties of the conditional independence relation to infer novel independences from known ones, thus avoiding the performance of statistical tests to estimate them. To accomplish this efficiently GSIMN uses the Triangle theorem, also introduced in this work, which is a simplified version of the set of Markov axioms. Experimental comparisons on artificial and real-world data sets show GSIMN can yield significant savings with respect to GSMN*, while generating a Markov network with comparable or in some cases improved quality. We also compare GSIMN to a forward-chaining implementation, called GSIMN-FCH, that produces all possible conditional independences resulting from repeatedly applying Pearl's theorems on the known conditional independence tests. The results of this comparison show that GSIMN, by the sole use of the Triangle theorem, is nearly optimal in terms of the set of independences tests that it infers.

This paper describes a novel approach based on a combination of techniques in AI, parallel computing, and network science to address an important problem in social sciences and public health: planning and responding in the event of epidemics. Spread of infectious disease is an important societal problem -- human behavior, social networks, and the civil infrastructures all play a crucial role in initiating and controlling such epidemic processes.  We specifically consider the economic and social effects of realistic interventions  proposed and adopted by public health officials and behavioral changes  of  private citizens in the event of a ``flu-like'' epidemic. Our results provide new insights for developing robust public policies that can prove useful for epidemic planning.

Multiagent planning and coordination problems are common and known to be computationally hard. We show that a wide range of two-agent problems can be formulated as bilinear programs. We present a successive approximation algorithm that significantly outperforms the coverage set algorithm, which is the state-of-the-art method for this class of multiagent problems. Because the algorithm is formulated for bilinear programs, it is more general and simpler to implement. The new algorithm can be terminated at any time and-unlike the coverage set algorithm-it facilitates the derivation of a useful online performance bound. It is also much more efficient, on average reducing the computation time of the optimal solution by about four orders of magnitude. Finally, we introduce an automatic dimensionality reduction method that improves the effectiveness of the algorithm, extending its applicability to new domains and providing a new way to analyze a subclass of bilinear programs.

Most subfields of computer science have an interface layer via which applications communicate with the infrastructure, and this is key to their success (e.g., the Internet in networking, the relational model in databases, etc.). So far this interface layer has been missing in AI. First-order logic and probabilistic graphical models each have some of the necessary features, but a viable interface layer requires combining both. Markov logic is a powerful new language that accomplishes this by attaching weights to first-order formulas and treating them as templates for features of Markov random fields. Most statistical models in wide use are special cases of Markov logic, and first-order logic is its infinite-weight limit.