Heuristic search is a central component of many important applications in AI including automated planning.  While we can find  optimal solutions to heuristic search problems, doing so may take hours or days. For practical applications, this is unacceptably slow, and we must rely on algorithms which find solutions of high, but not optimal, quality or ones which bound the time used directly. In my dissertation, I present and analyze algorithms for the following settings: quality bounded heuristic search and time  bounded heuristic search. The central theme of my doctoral work will be that taking advantage of additional information can improve the performance of heuristic search algorithms.

However, little is known regarding which algorithm is heuristic graph search algorithms. The analysis better in practice or the actual benefits of heuristic information is focused on the influence of heuristic information, in multiobjective search performance.

My research proposes to speed up grid-based pathfinding by identifying and eliminating symmetric path segments from the search space. Two paths are said to be symmetric if they are identical save for the order in which the individual moves (or steps) occur. To deal with path symmetries I decompose an arbitrary grid map into a set of empty rectangles and remove from each rectangle all interior nodes and possibly some from along the perimeter. A series of macro edges are then added between selected pairs of remaining nodes in order to facilitate provably optimal traversal through each rectangle. The new algorithm, Rectangular Symmetry Reduction (RSR), can speed up A* search by up to 38 times on a range of uniform cost maps taken from the literature. In addition to being fast and optimal, RSR requires no significant extra memory and is largely orthogonal all existing speedup techniques. When compared to the state of the art, RSR often shows significant improvement across a range of benchmarks.

Distributed Constraint Optimization Problems (DCOPs) can be optimally solved by distributed search algorithms, such as ADOPT and BnB-ADOPT. In centralized solving, maintaining soft arc consistency during search has proved to be beneficial for performance. In this thesis we aim to explore the maintenance of different levels of soft arc consistency in distributed search when solving DCOPs.

The process of extracting useful knowledge from large datasets has become one of the most pressing problems in today’s society. The problem spans entire sectors, from scientists to intelligence analysts and web users, all of whom are constantly struggling to keep up with the larger and larger amounts of content published every day. With this much data, it is often easy to miss the big picture. In this paper, we investigate methods for automatically connecting the dots – providing a structured, easy way to navigate within a new topic and discover hidden connections. We focus on the news domain: given two news articles, our system automatically finds a coherent chain linking them together. For example, it can recover the chain of events leading from the decline of home prices (2007) to the health-care debate (2009). We formalize the characteristics of a good chain and provide efficient algorithms to connect two fixed endpoints. We incorporate user feedback into our framework, allowing the stories to be refined and personalized. Finally, we evaluate our algorithm over real news data. Our user studies demonstrate the algorithm's effectiveness in helping users understanding the news.

This paper presents a new Monte-Carlo search algorithm for very large sequential decision-making problems. We apply non-linear regression within Monte-Carlo search, online, to estimate a state-action value function from the outcomes of random roll-outs. This value function generalizes between related states and actions, and can therefore provide more accurate evaluations after fewer rollouts. A further significant advantage of this approach is its ability to automatically extract and leverage domain knowledge from external sources such as game manuals. We apply our algorithm to the game of Civilization II, a challenging multi-agent strategy game with an enormous state space and around 10^21 joint actions. We approximate the value function by a neural network, augmented by linguistic knowledge that is extracted automatically from the official game manual. We show that this non-linear value function is significantly more efficient than a linear value function, which is itself more efficient than Monte-Carlo tree search. Our non-linear Monte-Carlo search wins over 78% of games against the built-in AI of Civilization II.

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.

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 investigates the effectiveness of two state representations, CNF and DNF, in contingent planning. To this end, we developed a new contingent planner, called CNFct, using the AND/OR forward search algorithm PrAO [To et al., 2011] and an extension of the CNF representation of [To et al., 2010] for conformant planning to handle nondeterministic and sensing actions for contingent planning. The study uses CNFct and DNFct [To et al., 2011] and proposes a new heuristic function for both planners. The experiments demonstrate that both CNFct and DNFct offer very competitive performance in a large range of benchmarks but neither of the two representations is a clear winner over the other. The paper identifies properties of the representation schemes that can affect their performance on different problems.

Planning under uncertainty for multiagent systems can be formalized as a decentralized partially observable Markov decision process. We advance the state of the art for optimal solution of this model, building on the Multiagent A* heuristic search method. A key insight is that we can avoid the full expansion of a search node that generates a number of children that is doubly exponential in the node's depth. Instead, we incrementally expand the children only when a next child might have the highest heuristic value. We target a subsequent bottleneck by introducing a more memory-efficient representation for our heuristic functions. Proof is given that the resulting algorithm is correct and experiments demonstrate a significant speedup over the state of the art, allowing for optimal solutions over longer horizons for many benchmark problems.