All in One: Multi-Task Prompting for Graph Neural Networks (Extended Abstract)
Abstract
In classical planning, conditional effects (CEs) allow modelling non-idempotent actions, where the resulting state may depend on how many times each action is consecutively repeated. Though CEs have been widely studied in the literature, no one has ever studied how to exploit rolling, i.e., how to effectively model the consecutive repetition of an action. In this paper, we fill this void by (i) showing that planning with CEs remains PSPACE-complete even in the limit case of problems with a single action, (ii) presenting a correct and complete planning as satisfiability encoding exploiting rolling while effectively dealing with constraints imposed on the set of reachable states, and (iii) theoretically and empirically showing its substantial benefits.
Cite
Text
Sun et al. "All in One: Multi-Task Prompting for Graph Neural Networks (Extended Abstract)." International Joint Conference on Artificial Intelligence, 2024. doi:10.24963/ijcai.2024/942Markdown
[Sun et al. "All in One: Multi-Task Prompting for Graph Neural Networks (Extended Abstract)." International Joint Conference on Artificial Intelligence, 2024.](https://mlanthology.org/ijcai/2024/sun2024ijcai-all/) doi:10.24963/ijcai.2024/942BibTeX
@inproceedings{sun2024ijcai-all,
title = {{All in One: Multi-Task Prompting for Graph Neural Networks (Extended Abstract)}},
author = {Sun, Xiangguo and Cheng, Hong and Li, Jia and Liu, Bo and Guan, Jihong},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2024},
pages = {8460-8465},
doi = {10.24963/ijcai.2024/942},
url = {https://mlanthology.org/ijcai/2024/sun2024ijcai-all/}
}