analiza aiqbench
This research addresses the critical challenge of balancing competing objectives—safety, energy efficiency, and time—in autonomous heavy-duty vehicles using multi-objective reinforcement learning. By employing a preference-conditioned framework, the study demonstrates how to generate interpretable trade-off curves without retraining models for different driving scenarios. The work advances practical RL applications in commercial transportation by explicitly modeling Pareto fronts rather than relying on simplified scalar rewards.
Preference-Conditioned Multi-Objective Reinforcement Learning for Tactical Decision Making in Heavy-Duty Vehicles
arXiv:2601.18783v3 Announce Type: replace Abstract: A central difficulty in applying reinforcement learning to real-world applications such as autonomous driving is that conventional scalar reward formulations obtained by aggregating multiple often competing objectives may obscure the structure of their trade-offs. These challenges are particularly relevant to decision-making for heavy-duty vehicles, which requires balancing safety, efficiency, and operational costs under demanding commercial requirements. We present a preference-conditioned multi-objective reinforcement learning framework that explicitly represents these objectives and utilizes Generalized Policy Improvement and Proximal Policy Optimization to learn policies capturing different trade-offs between them. The proposed method approximates the Pareto front across three conflicting objectives: safety, quantified in terms of collisions and successful completion; energy efficiency, quantified using energy cost; and time efficiency, quantified using driver cost. We evaluate the framework in a scalable highway traffic simulation environment tailored for tactical decision making in heavy-duty trucks. It yields smooth and interpretable Pareto fronts, and evaluations across traffic densities and against an analytical baseline show that the learned policies capture meaningful trade-offs. The preference-conditioned policy enables transitions between different driving behaviors without retraining, demonstrating the potential of multi-objective reinforcement learning for adaptive decision making in autonomous heavy-duty vehicles.
Abstract:A central difficulty in applying reinforcement learning to real-world applications such as autonomous driving is that conventional scalar reward formulations obtained by aggregating multiple often competing objectives may obscure the structure of their trade-offs. These challenges are particularly relevant to decision-making for heavy-duty vehicles, which requires balancing safety, efficiency, and operational costs under demanding commercial requirements. We present a preference-conditioned multi-objective reinforcement learning framework that explicitly represents these objectives and utilizes Generalized Policy Improvement and Proximal Policy Optimization to learn policies capturing different trade-offs between them. The proposed method approximates the Pareto front across three conflicting objectives: safety, quantified in terms of collisions and successful completion; energy efficiency, quantified using energy cost; and time efficiency, quantified using driver cost. We evaluate the framework in a scalable highway traffic simulation environment tailored for tactical decision making in heavy-duty trucks. It yields smooth and interpretable Pareto fronts, and evaluations across traffic densities and against an analytical baseline show that the learned policies capture meaningful trade-offs. The preference-conditioned policy enables transitions between different driving behaviors without retraining, demonstrating the potential of multi-objective reinforcement learning for adaptive decision making in autonomous heavy-duty vehicles.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Systems and Control (eess.SY)
arXiv:2601.18783 [cs.LG]
(or arXiv:2601.18783v3 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2601.18783 Focus to learn more arXiv-issued DOI via DataCite
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.
Text integral sub licența deschisă a publicației · 288 cuvinte
Subiecte conexe
Emotional Preferences as Goal-Priority Regulation
arXiv · 28 aug. 2026
The Continual Constitutional Convention: How language models revise the documents that govern them
AI Alignment Forum · 13 oct. 2026
The Alignment Problem: Computer Science Meets Analytic Philosophy
LessWrong · 18 oct. 2026
Learning Coordinated Preference for Multi-Objective Multi-Agent Reinforcement Learning
arXiv · 15 iun. 2026