EUVIMEDOpdag EUVIMED
Open access · CC BY 4.0

Hierarchical Two-Agent Reinforcement Learning for Long-Horizon Energy Optimization and Short-Horizon Navigation in Autonomous Electric Boats

Zamirddine Mari, Quentin Vassard, Mohamad Motasem Nawaf, Jérôme Pasquet

Sensors · 2026-11-13 · 26 (22) · 7167

DOI: 10.3390/s26227167 ↗

At a glance

Journal article in Sensors, published online on 2026-11-13. Written by Zamirddine Mari and 3 co-authors. 38 references. The full text is freely available (open access, CC BY 4.0).

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

This paper presents a hierarchical two-agent deep reinforcement learning architecture for an electric racing boat, addressing the joint challenges of long-horizon energy management and short-horizon autonomous navigation. The system integrates two independently trained agents: an energy optimization agent based on an importance-weighted actor–learner architecture, selected for its ability to handle long-horizon decision-making and distributed training, and a navigation agent trained with Proximal Policy Optimization, chosen for its training stability. The navigation policy tracks a target speed issued by the energy agent for each track segment. This target speed is the only coupling between the two levels. A curriculum learning strategy is used for both tasks. In a race simulator calibrated on real telemetry, the energy agent reaches the full 34-lap configuration, with a training success rate of 0.51 on average and about 0.72 at the end of training, while the navigation agent reaches its 0.80 evaluation success criterion under a ±5 km/h tolerance. A Unity3D-based environment with hydrodynamic modeling and autopilot software-in-the-loop emulation provides a framework for validation prior to on-water deployment; the closed-loop evaluation of the coupled agents remains future work.

Cite

APA

Mari, Z., Vassard, Q., Nawaf, M. M., & Pasquet, J. (2026). Hierarchical Two-Agent Reinforcement Learning for Long-Horizon Energy Optimization and Short-Horizon Navigation in Autonomous Electric Boats. Sensors, 26(22), 7167. https://doi.org/10.3390/s26227167

Vancouver

Mari Z, Vassard Q, Nawaf MM, Pasquet J. Hierarchical Two-Agent Reinforcement Learning for Long-Horizon Energy Optimization and Short-Horizon Navigation in Autonomous Electric Boats. Sensors. 2026;26(22):7167. doi:10.3390/s26227167

BibTeX
@article{Mari2026,
  author = {Mari, Zamirddine and Vassard, Quentin and Nawaf, Mohamad Motasem and Pasquet, Jérôme},
  title = {Hierarchical Two-Agent Reinforcement Learning for Long-Horizon Energy Optimization and Short-Horizon Navigation in Autonomous Electric Boats},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {22},
  pages = {7167},
  doi = {10.3390/s26227167}
}
Start for free →