works on
contrastive learning 1label noise robustness 1offline RL 1preference-based reinforcement learning 1reward alignment 1

From the 1 of 1 linked paper with an AI index.

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2026

Similarity as Reward Alignment: Robust and Versatile Preference-based Reinforcement Learning

Sara Rajaram, R. James Cotton, Fabian H. Sinz

The paper proposes SARA, a contrastive method that learns latent representations of preferred behaviors and uses similarity as a reward signal, improving robustness to noisy human…