Suboptimal heuristic search algorithms such as weighted A* and greedy best-first search are widely used to solve problems for which guaranteed optimal solutions are too expensive to obtain. These algorithms crucially rely on a heuristic function to guide their search. However, most research on building heuristics addresses optimal solving. In this paper, we illustrate how established wisdom for constructing heuristics for optimal search can fail when considering suboptimal search. We consider the behavior of greedy best-first search in detail and we test several hypotheses for predicting when a heuristic will be effective for it. Our results suggest that a predictive characteristic is a heuristic's goal distance rank correlation (GDRC), a robust measure of whether it orders nodes according to distance to a goal. We demonstrate that GDRC can be used to automatically construct abstraction-based heuristics for greedy best-first search that are more effective than those built by methods oriented toward optimal search. These results reinforce the point that suboptimal search deserves sustained attention and specialized methods of its own.
Search in general, and heuristic search in particular, is at the heart of many Artificial Intelligence algorithms and applications. There is now a growing and active community devoted to the empirical and theoretical study of heuristic search algorithms, thanks to the successful application of search-based algorithms to areas such as robotics, domain-independent planning, optimization, and computer games. In this extended abstract we highlight recent efforts in understanding suboptimal search algorithms, as well as ensembles of heuristics and algorithms. The result of these efforts are meta-reasoning methods which are applied to orchestrate the different components of modern search algorithms. Finally, we mention recent innovative applications of search that demonstrate the relevance of the field to general AI.
While suboptimal best-first search algorithms like Greedy Best-First Search are frequently used when building automated planning systems, their greedy nature can make them susceptible to being easily misled by flawed heuristics. This weakness has motivated the development of best-first search variants like epsilon-greedy node selection, type-based exploration, and diverse best-first search, which all use random exploration to mitigate the impact of heuristic error. In this paper, we provide a theoretical justification for this increased robustness by formally analyzing how these algorithms behave on infinite graphs. In particular, we show that when using these approaches on any infinite graph, the probability of not finding a solution can be made arbitrarily small given enough time. This result is shown to hold for a class of algorithms that includes the three mentioned above, regardless of how misleading the heuristic is.
It has been shown recently that the performance of greedy best-first search (GBFS) for computing plans that are not necessarily optimal can be improved by adding forms of exploration when reaching heuristic plateaus: from random walks to local GBFS searches. In this work, we address this problem but using structural exploration methods resulting from the ideas of width-based search. Width-based methodsseek novel states, are not goal oriented, and their power has been shown recently in the Atari and GVG-AI video-games. We show first that width-based exploration in GBFS is more effective than GBFS with local GBFS search (GBFS-LS), and then proceed to formulate a simple and general computational framework where standard goal-oriented search (exploitation) and width-based search (structural exploration) are combined to yield a search scheme, best-first width search, that is better than both and which results in classical planning algorithms that outperform the state-of-the-art planners.
We present several new algorithms for bidirectional best-first search that employ a front-to-front strategy of estimating distances from newly-generated frontier nodes in one search direction to existing frontier nodes in the other search direction, rather than estimating distances to terminal nodes in both searches. Unlike previous front-to-front strategies that use a shared priority queue to manage both frontiers, we use a separate data structure for each search, and choose that data structure to minimize the amount of computational effort required by the best-first search algorithm it supports. We demonstrate several results. First, we show that Bidirectional Front-to-Front Greedy (BFFG) is able to quickly find sub-optimal solutions to very large statespace problems and with a small fraction of nodes expanded (and stored) compared to other unidirectional and bidirectional greedy techniques. Secondly, we show that Bidirectional Front-to-Front A* (BFFA*) similarly outperforms both Unidirectional A* and Bidirectional Front-to-End A* (BFEA*) in terms of node expansions when searching for optimal solutions. Finally, we describe three improvements to BFFA*, each of which reduces the overall runtime by limiting the number of opposing frontier nodes that need be considered while preserving the optimality criterion.