{"type":"ScholarlyArticle","title":"Efficient Black-Box Planning Using Macro-Actions with Focused Effects","authors":[{"name":"Cameron Allen","slug":"cameron-allen","given":"Cameron","family":"Allen","affiliation":""},{"name":"Michael Katz","slug":"michael-katz","given":"Michael","family":"Katz","affiliation":""},{"name":"Tim Klinger","slug":"tim-klinger","given":"Tim","family":"Klinger","affiliation":""},{"name":"George Konidaris","slug":"george-konidaris","given":"George","family":"Konidaris","affiliation":""},{"name":"Matthew Riemer","slug":"matthew-riemer","given":"Matthew","family":"Riemer","affiliation":""},{"name":"Gerald Tesauro","slug":"gerald-tesauro","given":"Gerald","family":"Tesauro","affiliation":""}],"abstract":"The difficulty of deterministic planning increases exponentially with search-tree depth. Black-box planning presents an even greater challenge, since planners must operate without an explicit model of the domain. Heuristics can make search more efficient, but goal-aware heuristics for black-box planning usually rely on goal counting, which is often quite uninformative. In this work, we show how to overcome this limitation by discovering macro-actions that make the goal-count heuristic more accurate. Our approach searches for macro-actions with focused effects (i.e. macros that modify only a small number of state variables), which align well with the assumptions made by the goal-count heuristic. Focused macros dramatically improve black-box planning efficiency across a wide range of planning domains, sometimes beating even state-of-the-art planners with access to a full domain model.","doi":"10.24963/ijcai.2021/554","url":"https://ijcai.org/proceedings/2021/554","pdf":"https://ijcai.org/proceedings/2021/0554.pdf","markdown":"https://ijcai.org/proceedings/2021/554.md","bibtex":"https://ijcai.org/proceedings/2021/bibtex/554","volume":{"slug":"2021","title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2021","url":"https://ijcai.org/proceedings/2021/","year":2021,"location":"Montreal","dates":"19-27 August 2021","editors":"Prof. Zhi-Hua Zhou","isbn":"978-0-9992411-9-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2021"},"section":"Planning and Scheduling","track":"Main Track","number":554,"pages":{"first":4024,"last":4031},"keywords":["Planning and Scheduling: Planning and Scheduling","Planning and Scheduling: Search in Planning and Scheduling","Heuristic Search and Game Playing: Heuristic Search"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}