Reinforcement Learning with Comparative Evidence for Social Intelligence
Developing socially intelligent AI remains heavily dependent on human-annotated data, limiting the scale and breadth of social understanding models can acquire. Methods that derive training signals from unlabeled data offer a path beyond this dependence, but social predictions lack the verification oracles available in...
Keane Ong, Yuriel Ryan, Sabri Boughorbel et al.
· 0 citations