LLMs can create interpretable reward functions, using natural language task descriptions and objects. Comic created using Adobe Firefly.
×
OCALM: Object-Centric Assessment with Language Models
Paper
RLC 2024 - RLBrew Workshop
Poster
RLC 2024 - RLBrew Workshop
Corresponding Authors
Timo Kaufmann
Jannis Blüml
Quentin Delfosse
Code
Github Repository
If you like our work, feel free to share it.
Share this Paper
https://ml-research.github.io/people/jblueml/papertrees/ocalm
Copy Link
Close
Share
