Exploiting Learned Policies in Focal Search

TL;DR

This paper explores integrating neural network policies into Focal Search to improve bounded-suboptimal search efficiency, providing mathematical foundations and empirical evaluations across benchmarks and the 15-puzzle.

Contribution

It introduces novel methods for embedding learned policies into Focal Search with theoretical support and evaluates their performance on synthetic and real-world problems.

Findings

Discrepancy Focal Search outperforms other variants in runtime and solution quality.

The approach effectively leverages neural policies with varying accuracy levels.

Mathematical foundations support the proposed algorithms.

Abstract

Recent machine-learning approaches to deterministic search and domain-independent planning employ policy learning to speed up search. Unfortunately, when attempting to solve a search problem by successively applying a policy, no guarantees can be given on solution quality. The problem of how to effectively use a learned policy within a bounded-suboptimal search algorithm remains largely as an open question. In this paper, we propose various ways in which such policies can be integrated into Focal Search, assuming that the policy is a neural network classifier. Furthermore, we provide mathematical foundations for some of the resulting algorithms. To evaluate the resulting algorithms over a number of policies with varying accuracy, we use synthetic policies which can be generated for a target accuracy for problems where the search space can be held in memory. We evaluate our focal search variants over three benchmark domains using our synthetic approach, and on the 15-puzzle using a neural network learned using 1.5 million examples. We observe that Discrepancy Focal Search, which we show expands the node which maximizes an approximation of the probability that its corresponding path is a prefix of an optimal path, obtains, in general, the best results in terms of runtime and solution quality.