Skip to content

QuickLAP: Quick Language–Action Preference Learning for real-time multimodal reward inference in autonomous driving. A Bayesian framework that fuses physical corrections and natural-language feedback to learn user reward functions online.

License

Notifications You must be signed in to change notification settings

MIT-CLEAR-Lab/QuickLAP

About

QuickLAP: Quick Language–Action Preference Learning for real-time multimodal reward inference in autonomous driving. A Bayesian framework that fuses physical corrections and natural-language feedback to learn user reward functions online.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages