HDA* is a simple, parallelization of A* where work is asynchronously distributed among the nodes by a global hash function. Using up to 1024 cores on a large distributed memory cluster, we evaluate HDA* for a domain-independent planner as well an application-specific 24-puzzle solver. We show that HDA* scales fairly well on a large cluster using up to 1024 cores. Our analysis of the scaling behavior shows that on a cluster of multicore nodes, using only a subset of the available cores and leaving some cores idle can, surprisingly, lead to better results.

In this paper we explore a novel approach for anytime heuristic search, in which the node that is most probable to improve the incumbent solution is expanded first. This is especially suited for the "anytime aspect" of anytime algorithms - the possibility that the algorithm will be be halted anytime throughout the search. The potential of a node to improve the incumbent solution is estimated by a custom cost function, resulting in Potential Search, an anytime best-first search. Experimental results on the 15-puzzle and on the key player problem in communication networks (KPP-COM) show that this approach is competitive with state-of-the-art anytime heuristic search algorithms, and is more robust.

We present a new heuristic point-to-point shortest path algorithm based on contraction hierarchies (CH). Given an epsilon >= 0, we can prove that the length of the path computed by our algorithm is at most (1 + ε) times the length of the optimal (shortest) path. Exact CH is based on node contraction: removing nodes from a network and adding shortcuts to preserve shortest path distances. Our heuristic CH tries to avoid adding shortcuts even when a replacement path is (1+epsilon) times longer. However, we cannot avoid all such shortcuts, as we need to ensure that errors do not stack. Combinations with goal-directed techniques bring further speed-ups.

Bounded suboptimal search algorithms attempt to find a solution quickly while guaranteeing that the cost does not exceed optimal by more than a desired factor. These algorithms generally use a single admissible heuristic both for guidance and guaranteeing solution quality. We present a new approach to bounded suboptimal search that separates these roles, consulting multiple sources of potentially inadmissible information to determine search order and using admissible information to guarantee quality. An empirical evaluation across six benchmark domains shows the new approach has better overall performance.

Branch-and-Bound search is a basic algorithm for solving combinatorial optimization problems. Here we introduce a new lower-bounding methodology that can be incorporated into any branch-and-bound solver, and demonstraint its use on the MaxSAT constraint optimization problem. The approach is to adapt a “minimum-height equivalent transformation” framework that was first developed in the context of computer vision. We present efficient algorithms to realize this framework within the MaxSAT domain, and demonstrate their feasibility by implementing them within the state-of-the-art maxsatz solver. We evaluate the solver on test sets from the 2009 MaxSAT competition; we observe a basic performance tradeoff whereby the (quadratic) time cost of computing the transformations may or may not be worthwhile in exchange for better bounds and more frequent pruning. For specific test sets, the trade-off does result in significant improvement in both prunings and overall run-time.

We introduce a new bidirectional search algorithm, Single-Frontier Bidirectional Search (SFBDS). Unlike traditional BDS which keeps two frontiers, SFBDS uses a single frontier. At a particular node we can decide to search from start to goal or from goal to start, choosing the direction with the highest potential for minimizing the total work done. We provide theoretical analysis that explains when SFBDS will work validated by experimental results.

search algorithms such as IDA* or heuristic-search planners. Our method aims to generate a strong heuristic from a given weak heuristic h 0 through bootstrapping. The "easy" problem instances that can be solved using h 0 provide training examples for a learning algorithm that produces a heuristic h 1 that is expected to be stronger than h 0 . If h 0 is too weak to solve any of the given instances we use a random walk technique to create a sequence of successively more difficult instances starting with ones that are solvable by h 0 . The bootstrap process is then repeated using h i in lieu of h i –1 until a sufficiently strong heuristic is produced. We test our method on the 15- and 24-sliding tile puzzles, the 17- and 24-pancake puzzles, and the 15- and 20-blocks world. In every case our method produces a heuristic that allows IDA* to solve randomly generated problem instances extremely quickly with solutions very close to optimal.

Transposition tables are a well-known method for pruning duplicates in heuristic search. This paper presents a detailed analysis of transposition tables for IDA*. We show that some straightforward implementations of IDA* with transposition tables (IDA*+TT) can result in suboptimal solutions being returned. Furthermore, straightforward implementations of IDA*+TT are not complete. We identify several variants of IDA*+TT which are guaranteed to return the optimal solution, as well as a complete variant. An empirical study shows that IDA*+TT can significantly improve upon the performance of A* in domain-independent planning.

Constraint problems can be trivially solved in parallel by exploring different branches of the search tree concurrently. Previous approaches have focused on implementing this functionality in the solver, more or less transparently to the user. We propose a new approach, which modifies the constraint model of the problem. An existing model is split into new models with added constraints that partition the search space. Optionally, additional constraints are imposed that rule out the search already done. The advantages of our approach are that it can be implemented easily, computations can be stopped and restarted, moved to different machines and indeed solved on machines which are not able to communicate with each other at all.

A key factor that can dramatically reduce the search space during constraint solving is the criterion under which the variable to be instantiated next is selected. For this purpose numerous heuristics have been proposed. Some of the best of such heuristics exploit information about failures gathered throughout search and recorded in the form of constraint weights, while others measure the importance of variable assignments in reducing the search space. In this work we experimentally evaluate the most recent and powerful variable ordering heuristics, and new variants of them, over a wide range of benchmarks. Results demonstrate that heuristics based on failures are in general more efficient. Based on this, we then derive new revision ordering heuristics that exploit recorded failures to efficiently order the propagation list when arc consistency is maintained during search. Interestingly, in addition to reducing the number of constraint checks and list operations, these heuristics are also able to cut down the size of the explored search tree.