Counterplanning Using Goal Recognition and Landmarks
Abstract
In non-cooperative multi-agent systems, agents might want to prevent the opponents from achieving their goals. One alternative to solve this task would be using counterplanning to generate a plan that allows an agent to block other's to reach their goals. In this paper, we introduce a fully automated domain-independent approach for counterplanning. It combines; goal recognition to infer an opponent's goal; landmarks' computation to identify subgoals that can be used to block opponents' goals achievement; and classical automated planning to generate plans that prevent the opponent's goals achievement. Experimental results in several domains show the benefits of our novel approach.
Cite
Text
Pozanco et al. "Counterplanning Using Goal Recognition and Landmarks." International Joint Conference on Artificial Intelligence, 2018. doi:10.24963/IJCAI.2018/668Markdown
[Pozanco et al. "Counterplanning Using Goal Recognition and Landmarks." International Joint Conference on Artificial Intelligence, 2018.](https://mlanthology.org/ijcai/2018/pozanco2018ijcai-counterplanning/) doi:10.24963/IJCAI.2018/668BibTeX
@inproceedings{pozanco2018ijcai-counterplanning,
title = {{Counterplanning Using Goal Recognition and Landmarks}},
author = {Pozanco, Alberto and E-Martín, Yolanda and Fernández, Susana and Borrajo, Daniel},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2018},
pages = {4808-4814},
doi = {10.24963/IJCAI.2018/668},
url = {https://mlanthology.org/ijcai/2018/pozanco2018ijcai-counterplanning/}
}