We discuss a novel approach for dealing with single-stage stochastic constraint satisfaction problems (SCSPs) that include random variables over a continuous or large discrete support. Our approach is based on two novel tools: sampled SCSPs and (α,ϑ)-solutions. Instead of explicitly enumerating a very large or infinite set of future scenarios, we employ statistical estimation to determine if a given assignment is consistent for a SCSP. As in statistical estimation, the quality of our estimate is determined via confidence interval analysis. In contrast to existing approaches based on sampling, we provide likelihood guarantees for the quality of the solutions found. Our approach can be used in concert with existing strategies for solving SCSPs.

Imprecise-reward Markov decision processes (IRMDPs) are MDPs in which the reward function is only partially specified (e.g., by some elicitation process). Recent work using minimax regret to solve IRMDPs has shown, despite their theoretical intractability, how the set of policies that are nondominated w.r.t. reward uncertainty can be exploited to accelerate regret computation. However, the number of nondominated policies is generally so large as to undermine this leverage. In this paper, we show how the quality of the approximation can be improved online by pruning/adding nondominated policies during reward elicitation, while maintaining computational tractability. Drawing insights from the POMDP literature, we also develop a new anytime algorithm for constructing the set of nondominated policies with provable (anytime) error bounds. These bounds can be exploited to great effect in our online approximation scheme.

Specifying the reward function of a Markov decision process (MDP) can be demanding, requiring human assessment of the precise quality of, and tradeoffs among, various states and actions. However, reward functions often possess considerable structure which can be leveraged to streamline their specification. We develop new, decision-theoretically sound heuristics for eliciting rewards for factored MDPs whose reward functions exhibit additive independence. Since we can often find good policies without complete reward specification, we also develop new (exact and approximate) algorithms for robust optimization ofimprecise-reward MDPs with such additive reward. Our methods are evaluated in two domains: autonomic computing and assistive technology.

Predicting trust among the agents is of great importance to various open distributed settings (e.g., e-market, peer-to-peer networks, etc.) in that dishonest agents can easily join the system and achieve their goals by circumventing agreed rules, or gaining unfair advantages, etc. Most existing trust mechanisms derive trust by statistically investigating the target agent's historical information. However, even if rich historical information is available, it is challenging to model an agent's behavior since an intelligent agent may strategically change its behavior to maximize its profits. We therefore propose a trust prediction approach to capture dynamic behavior of the target agent. Specifically, we first identify features which are capable of describing/representing context of a transaction. Then we use these features to measure similarity between context of the potential transaction and that of previous transactions to estimate trustworthiness of the potential transaction based on previous similar transactions' outcomes. Evaluation using real auction data and synthetic data demonstrates efficacy of our approach in comparison with an existing representative trust mechanism.

Multiagent planning has seen much progress with the development of formal models such as Dec-POMDPs. However, the complexity of these models—NEXP-Complete even for two agents—has limited scalability. We identify certain mild conditions that are sufficient to make multiagent planning amenable to a scalable approximation w.r.t. the number of agents. This is achieved by constructing a graphical model in which likelihood maximization is equivalent to plan optimization. Using the Expectation-Maximization framework for likelihood maximization, we show that the necessary inference can be decomposed into processes that often involve a small subset of agents, thereby facilitating scalability. We derive a global update rule that combines these local inferences to monotonically increase the overall solution quality. Experiments on a large multiagent planning benchmark confirm the benefits of the new approach in terms of runtime and scalability.

How should we manage a sensor network to optimally guard security-critical infrastructure? How should we coordinate search and rescue helicopters to best locate survivors after a major disaster? In both applications, we would like to control sensing resources in uncertain, adversarial environments. In this paper, we introduce RSense, an efficient algorithm which guarantees near-optimal randomized sensing strategies whenever the detection performance satisfies submodularity, a natural diminishing returns property, for any fixed adversarial scenario. Our approach combines techniques from game theory with submodular optimization. The RSense algorithm applies to settings where the goal is to manage a deployed sensor network or to coordinate mobile sensing resources (such as unmanned aerial vehicles). We evaluate our algorithms on two real-world sensing problems.

We propose a new additive decomposition of probability tables that preserves equivalence of the joint distribution while reducing the size of potentials, without extra variables. We formulate the Most Probable Explanation (MPE) problem in belief networks as a Weighted Constraint Satisfaction Problem (WCSP). Our pairwise decomposition allows to replace a cost function with smaller-arity functions. The resulting pairwise decomposed WCSP is then easier to solve using state-of-the-art WCSP techniques. Although testing pairwise decomposition is equivalent to testing pairwise independence in the original belief network, we show how to efficiently test and enforce it, even in the presence of hard constraints. Furthermore, we infer additional information from the resulting nonbinary cost functions by projecting and subtracting them on binary functions. We observed huge improvements by preprocessing with pairwise decomposition and project&subtract compared to the current state-of-the-art solvers on two difficult sets of benchmark.

This paper is devoted to sequential decision making under uncertainty, in the multi-prior framework of Gilboa and Schmeidler [1989]. In this setting, a set of probability measures (priors) is defined instead of a single one, and the decision maker selects a strategy that maximizes the minimum possible value of expected utility over this set of priors. We are interested here in the resolute choice approach, where one initially commits to a complete strategy and never deviates from it later. Given a decision tree representation with multiple priors, we study the problem of determining an optimal strategy from the root according to min expected utility. We prove the intractability of evaluating a strategy in the general case. We then identify different properties of a decision tree that enable to design dedicated resolution procedures. Finally, experimental results are presented that evaluate these procedures.

We describe a generative Bayesian model for action understanding in which inverse-forward internal model pairs are considered "hypotheses" of plausible action goals that are explored in parallel via an approximate inference mechanism based on sequential Monte Carlo methods. The reenactment of internal model pairs can be considered a form of motor simulation, which supports both perceptual prediction and action understanding at the goal level. However, this procedure is generally considered to be computationally inefficient. We present a model that dynamically reallocates computational resources to more accurate internal models depending on both the available prior information and the prediction error of the inverse-forward models, and which leads to successful action recognition. We present experimental results that test the robustness and efficiency of our model in real-world scenarios.

This paper considers inference from multinomial data and addresses the problem of choosing the strength of the Dirichlet prior under a mean-squared error criterion. We compare the Maximum Likelihood Estimator (MLE) and the most commonly used Bayesian estimators obtained by assuming a prior Dirichlet distribution with non-informative prior parameters, that is, the parameters of the Dirichlet are equal and altogether sum up to the so called strength of the prior. Under this criterion, MLE becomes more preferable than the Bayesian estimators at the increase of the number of categories k of the multinomial, because non-informative Bayesian estimators induce a region where they are dominant that quickly shrinks with the increase of k. This can be avoided if the strength of the prior is not kept constant but decreased with the number of categories. We argue that the strength should decrease at least k times faster than usual estimators do.