Responsibility Anticipation and Attribution in LTLf
Abstract
Responsibility is one of the key notions in machine ethics and in the area of autonomous systems. It is a multi-faceted notion involving counterfactual reasoning about actions and strategies. In this paper, we study different variants of responsibility for LTLf outcomes based on strategic reasoning. We show a connection with notions in reactive synthesis, including the synthesis of winning, dominant, and best-effort strategies. This connection provides a strong computational grounding of responsibility, allowing us to characterize the worst-case computa- tional complexity and devise sound, complete, and optimal algorithms for anticipating and attributing responsibility.
Cite
Text
De Giacomo et al. "Responsibility Anticipation and Attribution in LTLf." International Joint Conference on Artificial Intelligence, 2025. doi:10.24963/IJCAI.2025/6Markdown
[De Giacomo et al. "Responsibility Anticipation and Attribution in LTLf." International Joint Conference on Artificial Intelligence, 2025.](https://mlanthology.org/ijcai/2025/giacomo2025ijcai-responsibility/) doi:10.24963/IJCAI.2025/6BibTeX
@inproceedings{giacomo2025ijcai-responsibility,
title = {{Responsibility Anticipation and Attribution in LTLf}},
author = {De Giacomo, Giuseppe and Lorini, Emiliano and Parker, Timothy and Parretti, Gianmarco},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2025},
pages = {47-55},
doi = {10.24963/IJCAI.2025/6},
url = {https://mlanthology.org/ijcai/2025/giacomo2025ijcai-responsibility/}
}