UT Austin's Rewarding Lab
ActiveResearch focus
We primarily focus on the specification of human-aligned reward functions for reinforcement learning (RL). This effort involves studying how human RL experts design reward functions, how to interpret preference annotations, and theory focused on reward functions.
Open to collaboration
No
Looking for
We collaborate heavily with a small group of similarly focused researchers but are not seeking to expand the lab immediately. If you are doing research on the problem of reward function specification in the broad sense that an RL practitioner interprets it (not only myopic reward for LLM fine-tuning) and are doing so in an institutional setting, I'd still like to make your acquaintance and know about your interests and work.
Contact
Join the Damaqu community to see this team's full profile.