A Behavior-first approach to Multi-Intention Inverse Reinforcement Learning

Abstract:Inverse Reinforcement Learning (IRL) seeks to infer reward functions from expert demonstrations. When demonstrations originate from multiple experts with different intentions, the problem is known as Multi-Intention IRL (MI-IRL). Recent deep generative MI-IRL approaches couple behavior clustering and reward learning, but typically require prior knowledge of the number of true behavioral modes $K^*$. This reliance on expert knowledge limits their adaptability to new behaviors, and only enables analysis related to the learned rewards, and not across the behavior modes used to train them. We propose Contrastive Multi-Intention IRL (CoMI-IRL), a transformer-based unsupervised framework that decouples behavior representation and clustering from downstream reward learning. Our experiments show that CoMI-IRL outperforms existing approaches without a priori knowledge of $K^*$ or labels, while allowing for visual interpretation of behavior relationships and adaptation to unseen behavior without full retraining.

33 pages, 11 figures, 20 tables, Accepted to Transactions on Machine Learning Research (TMLR). OpenReview: this https URL

Machine Learning (cs.LG)

arXiv:2602.07496 [cs.LG]

(or arXiv:2602.07496v2 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2602.07496 Focus to learn more arXiv-issued DOI via DataCite

Transactions on Machine Learning Research, 2026. ISSN 2835-8856

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.