policy
VendeeGlobeRL
alessandrocampedelli · Stable-Baselines3
or hover any field below to flag it
Overview
Name
VendeeGlobeRL
Author
alessandrocampedelli
Framework
Stable-Baselines3
License
unknown
Skill type
navigation
Evidence level
untested
Task description
Reinforcement Learning agent (PPO + Stable-Baselines3) that autonomously navigates a simulated Vendée Globe round-the-world race using real ERA5 wind data. Trained on two historical seasons (2016–17, 2020–21), tested on unseen 2024–25 conditions. Built with a custom Gymnasium environment, IMOCA 60 p
Spaces
Action space
other · 0-dim · 0Hz
Observation space
- type: other
Links
HuggingFace repo
null
Paper (arXiv)
null
Compatible robots
3+17 mentioned but not in catalog yetCompatible environments
0No environments list VendeeGlobeRL yet.
Datasets that reference this policy
0No datasets reference VendeeGlobeRL yet.