Skip to main content

Efficient Black-Box Planning Using Macro-Actions with Focused Effects

Publication ,  Conference
Allen, C; Katz, M; Klinger, T; Konidaris, G; Riemer, M; Tesauro, G
Published in: IJCAI International Joint Conference on Artificial Intelligence
January 1, 2021

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.

Duke Scholars

Published In

IJCAI International Joint Conference on Artificial Intelligence

ISSN

1045-0823

ISBN

9780999241196

Publication Date

January 1, 2021

Start / End Page

4024 / 4031
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Allen, C., Katz, M., Klinger, T., Konidaris, G., Riemer, M., & Tesauro, G. (2021). Efficient Black-Box Planning Using Macro-Actions with Focused Effects. In IJCAI International Joint Conference on Artificial Intelligence (pp. 4024–4031).
Allen, C., M. Katz, T. Klinger, G. Konidaris, M. Riemer, and G. Tesauro. “Efficient Black-Box Planning Using Macro-Actions with Focused Effects.” In IJCAI International Joint Conference on Artificial Intelligence, 4024–31, 2021.
Allen C, Katz M, Klinger T, Konidaris G, Riemer M, Tesauro G. Efficient Black-Box Planning Using Macro-Actions with Focused Effects. In: IJCAI International Joint Conference on Artificial Intelligence. 2021. p. 4024–31.
Allen, C., et al. “Efficient Black-Box Planning Using Macro-Actions with Focused Effects.” IJCAI International Joint Conference on Artificial Intelligence, 2021, pp. 4024–31.
Allen C, Katz M, Klinger T, Konidaris G, Riemer M, Tesauro G. Efficient Black-Box Planning Using Macro-Actions with Focused Effects. IJCAI International Joint Conference on Artificial Intelligence. 2021. p. 4024–4031.

Published In

IJCAI International Joint Conference on Artificial Intelligence

ISSN

1045-0823

ISBN

9780999241196

Publication Date

January 1, 2021

Start / End Page

4024 / 4031