IJCAI 2025 Distinguished Paper Award for TU Wien Researchers
Congratulations to Emery Neufeld, Agata Ciabattoni, and Radu Tulcan on winning the IJCAI 2025 Distinguished Paper Award for their paper “Combining MORL with Restraining Bolts to Learn Normative Behaviour”! IJCAI 2025 was held in Montreal, Canada, from August 16 to August 22, 2025.
The IJCAI Distinguished Paper Awards recognize some of the best papers presented at the conference each year. This year, three articles were named as distinguished papers, and one of them is a paper presented by three researchers from TU Wien Informatics who are part of the WWTF-funded project TAIGER (Training and Guiding AI Agents with Ethical Rules). The winning paper was produced as part of project TAIGER as well as the FWF-funded Cluster of Excellence BILAI.
Combining MORL with Restraining Bolts to Learn Normative BehaviourEmery A. Neufeld, Agata Ciabattoni and Radu Florin Tulcan
Abstract: Normative Restraining Bolts (NRBs) adapt the restraining bolt technique (originally developed for safe reinforcement learning) to ensure compliance with social, legal, and ethical norms. While effective, NRBs rely on trial-and-error weight tuning, which hinders their ability to enforce hierarchical norms; moreover, norm updates require retraining. In this paper, we reformulate learning with NRBs as a multi-objective reinforcement learning (MORL) problem, where each norm is treated as a distinct objective. This enables the introduction of Ordered Normative Restraining Bolts (ONRBs), which support algorithmic weight selection, prioritized norms, norm updates, and provide formal guarantees on minimizing norm violations. Case studies show that ONRBs offer a robust and principled foundation for RL-agents to comply with a wide range of norms while achieving their goals.
Read the paper in full here.
ABOUT THE AUTHORS