Learning Macro-actions for State-Space Planning

TL;DR

This paper introduces an algorithm that learns macro-actions online using data mining, significantly improving planning efficiency across multiple benchmarks.

Contribution

It presents a novel method for automatically learning macro-actions during planning, enhancing scalability and performance.

Findings

Significant performance improvements on four classical benchmarks

Effective online macro-action learning algorithm

Demonstrated scalability and efficiency gains

Abstract

Planning has achieved significant progress in recent years. Among the various approaches to scale up plan synthesis, the use of macro-actions has been widely explored. As a first stage towards the development of a solution to learn on-line macro-actions, we propose an algorithm to identify useful macro-actions based on data mining techniques. The integration in the planning search of these learned macro-actions shows significant improvements over four classical planning benchmarks.