Learning Macro-actions for State-Space Planning

2016/10/07 by Sandra Castellanos-Paez, Damien Pellier, Castellanos-Paez, Sandra +5
Computer Science · #AI-based Problem Solving and Planning #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Reinforcement Learning in Robotics #Robotic Path Planning Algorithms #cs.AI

paper · pdf · doi:10.48550/arxiv.1610.02293

Journ{é}es Francophones sur la Planification, la D{é}cision et l'Apprentissage pour la conduite de syst{è}mes (JFPDA 2016) , Jul 2016, Grenoble, France. 2016

arxiv created 2016/10/07 · openalex publication_date 2016/10/07 · arxiv updated 2016/10/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Related

• Leveraging Action Relational Structures for Integrated Learning and Planning
• STRIPS Action Discovery
• Efficient Black-Box Planning Using Macro-Actions with Focused Effects
• On-the-fly Macros
• Discovering Underlying Plans Based on Distributed Representations of Actions