Moral Planning Agents with LTL Values
Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence. Main Track. Pages 418-426.
https://doi.org/10.24963/ijcai.2023/47
Keywords
- AI Ethics, Trust, Fairness: ETF: Moral decision making
- Knowledge Representation and Reasoning: KRR: Knowledge representation languages
- Agent-based and Multi-agent Systems: MAS: Normative systems
Abstract
A moral planning agent (MPA) seeks to compare two plans or compute an optimal plan in an interactive setting with other agents, where relative ideality and optimality of plans are defined with respect to a prioritized value base. We model MPAs whose values are expressed by formulas of linear temporal logic (LTL) and define comparison for both joint plans and individual plans. We introduce different evaluation criteria for individual plans including an optimistic (risk-seeking) criterion, a pessimistic (risk-averse) one, and two criteria based on the use of anticipated responsibility. We provide complexity results for a variety of MPA problems.
@inproceedings{ijcai2023p47,
title = {Moral Planning Agents with LTL Values},
author = {Grandi, Umberto and Lorini, Emiliano and Parker, Timothy},
booktitle = {Proceedings of the Thirty-Second International Joint Conference on
Artificial Intelligence, {IJCAI-23}},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
editor = {Edith Elkind},
pages = {418--426},
year = {2023},
month = {8},
note = {Main Track},
doi = {10.24963/ijcai.2023/47},
url = {https://doi.org/10.24963/ijcai.2023/47},
}
TY - CPAPER TI - Moral Planning Agents with LTL Values AU - Grandi, Umberto AU - Lorini, Emiliano AU - Parker, Timothy T2 - Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI-23 PB - International Joint Conferences on Artificial Intelligence Organization PY - 2023 SP - 418 EP - 426 DO - 10.24963/ijcai.2023/47 UR - https://doi.org/10.24963/ijcai.2023/47 ER -Copied
Machine-readable versions of this paper, for tools and AI agents: