publications

2026

1. 

   Cross-entropy optimization with prioritized constraints

   F. Roldan Sanchez, P. de las Heras Molins, D. Fridovich-Keil, and G. Bakirtzis

   preprint , 2026

   Abs arXiv Bib PDF

   When constraints conflict, an optimizer must determine which requirements to preserve and which to relax. On the one hand, a priority ordering specifies which requirements take precedence. On the other hand, penalty-based formulations encode their relative importance through numerical weights. Depending on these weights, a solution can improve its weighted score while violating intended priorities. We introduce TierCEM, a variant of the cross-entropy method that incorporates strict constraint priorities directly into elite selection without requiring per-constraint importance weights. TierCEM works by sequentially filtering sampled candidates, from highest- to lowest-priority constraint. If and when a constraint eliminates all remaining candidates, TierCEM returns to the last nonempty set and selects elites with the smallest violations of that blocking constraint, recursively preserving satisfaction of all higher-priority constraints. We evaluate TierCEM on 2D navigation and contact-rich pushing tasks in proprioceptive and learned world-model settings. Experiments show that reversing the constraint ordering changes which constraints are violated under conflict. Prioritizing progress toward the task objective also enables TierCEM to relax lower-priority constraints when they would otherwise prevent further progress.

   @misc{roldansanchez2026crossentropyoptimizationprioritizedconstraints,
     title = {Cross-entropy optimization with prioritized constraints},
     author = {Roldan Sanchez, F. and {de las Heras Molins}, P. and Fridovich-Keil, D. and Bakirtzis, G.},
     year = {2026},
     archiveprefix = {arXiv},
     primaryclass = {cs.RO},
     url = {https://arxiv.org/abs/2610.01319},
   }

2. 

   Cascaded consensus splitting for multi-branch contingency games

   B. Lechardoy, P. de las Heras Molins, T. Lahire, L. Pautet, D. Filliat, D. Fridovich-Keil, and G. Bakirtzis

   preprint , 2026

   Abs arXiv Bib PDF

   Contingency games enable agents to anticipate and plan for other agents’ hypothetical intents by constructing trajectories with a shared prefix and intent-dependent branches. While contingency games capture intent uncertainty, existing formulations rely on a single branching time, oversimplifying interactions in which different agents’ intentions are revealed at different times. Moreover, the computational cost of such problems grows rapidly with the number of agents and intents, as all scenario-dependent best responses must be solved jointly. We introduce a multi-branch contingency architecture in which sources of intent uncertainty can be resolved progressively at different branching times, allowing the planned trajectories to adapt to the asynchronous revelation of intents. We also develop an ADMM-based solver that exploits scenario-level parallelism. Experiments on tightly coupled three-agent interactions support that the proposed architecture outperforms the conventional single-branch while achieving a lower mean receding-horizon solve time.

   @misc{lechardoy2026cascadedconsensussplitting,
     title = {Cascaded consensus splitting for multi-branch contingency games},
     author = {Lechardoy, B. and {de las Heras Molins}, P. and Lahire, T. and Pautet, L. and Filliat, D. and Fridovich-Keil, D. and Bakirtzis, G.},
     year = {2026},
     archiveprefix = {arXiv},
     primaryclass = {cs.RO},
     url = {https://arxiv.org/abs/2609.37612},
   }

3. 

   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 arXiv Bib PDF Code 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{delasherasmolins2026controllability,
     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},
     archiveprefix = {arXiv},
     primaryclass = {cs.LG},
     url = {https://arxiv.org/abs/2605.10585},
   }

2025

1. 

   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 arXiv Bib PDF Code 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{delasherasmolins2025approximatesolutionsgamesorderedpreference,
     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},
     archiveprefix = {arXiv},
     primaryclass = {eess.SY},
     url = {https://arxiv.org/abs/2507.11021},
   }