Pau de las Heras Molins

news

Jul 2026	I visited the Oden Institute at UT Austin and gave a talk at the Center for Autonomy seminar: Preference in agent control.
Jun 2026	I visited LIDS at MIT and gave a talk to Gioele Zardini’s group: Preference in agent control.
Jun 2026	I visited the ICON lab at UC Berkeley and gave a talk: Preference in agent control.
Jun 2026	I attended the Reinforcement Learning Summer School (RLSS) at the Politecnico di Milano.
May 2026	I gave a talk at ISU in Cody Fleming’s group: Controlling multi-objective reinforcement learning agents through preference.
Apr 2026	Our work on the controllability of MORL agents has been accepted at NeuS 2026. See you in LA!
Mar 2026	I gave a talk at UMich in Inigo Incer’s group: Controlling multi-objective reinforcement learning agents through preference.

selected publications

Controllability in preference-conditioned multi-objective reinforcement learning

P. de las Heras Molins, B. Yalcinkaya, L. Peters, D. Fridovich-Keil, and G. Bakirtzis

International Conference on Neuro-Symbolic Systems (NeuS) , 2026

Abs Bib HTML PDF Poster

Multi-objective reinforcement learning (MORL) allows a user to express preference over outcomes in terms of the relative importance of the objectives, but standard metrics cannot capture whether changes in preference reliably change the agent’s behavior in the intended way, a property termed controllability. As a result, preference-conditioned agents can score well on standard MORL metrics while being insensitive to the preference input. If the ability to control agents cannot be reliably assessed, the symbolic interface that MORL provides between user intent and agent behavior is broken. Mainstream MORL metrics alone fail to measure the controllability of preference-conditioned agents, motivating a complementary metric specifically designed to that end. We hope the results spur discussion in the community on existing evaluation protocols to consolidate advances in preference adaptation in MORL to larger and more complex problems.
@misc{molins2026controllability, title = {Controllability in preference-conditioned multi-objective reinforcement learning}, author = {{de las Heras Molins}, P. and Yalcinkaya, B. and Peters, L. and Fridovich-Keil, D. and Bakirtzis, G.}, year = {2026}, eprint = {2605.10585}, archiveprefix = {arXiv}, primaryclass = {cs.LG}, url = {https://arxiv.org/abs/2605.10585}, }
Approximate solutions to games of ordered preference

P. de las Heras Molins^*, E. Roy-Almonacid^*, D. H. Lee, L. Peters, D. Fridovich-Keil, and G. Bakirtzis

IEEE International Conference on Intelligent Transportation Systems (ITSC) , 2025

Abs Bib HTML PDF Poster

Autonomous vehicles must balance ranked objectives, such as minimizing travel time, ensuring safety, and coordinating with traffic. Games of ordered preference effectively model these interactions but become computationally intractable as the time horizon, number of players, or number of preference levels increase. While receding horizon frameworks mitigate long-horizon intractability by solving sequential shorter games, often warm-started, they do not resolve the complexity growth inherent in existing methods for solving games of ordered preference. This paper introduces a solution strategy that avoids excessive complexity growth by approximating solutions using lexicographic iterated best response (IBR) in receding horizon, termed "lexicographic IBR over time." Lexicographic IBR over time uses past information to accelerate convergence. We demonstrate through simulated traffic scenarios that lexicographic IBR over time efficiently computes approximate-optimal solutions for receding horizon games of ordered preference, converging towards generalized Nash equilibria.
@misc{molins2025approximatesolutionsgamesordered, title = {Approximate solutions to games of ordered preference}, author = {{de las Heras Molins}, P. and Roy-Almonacid, E. and Lee, D. H. and Peters, L. and Fridovich-Keil, D. and Bakirtzis, G.}, year = {2025}, eprint = {2507.11021}, archiveprefix = {arXiv}, primaryclass = {eess.SY}, url = {https://arxiv.org/abs/2507.11021}, }