Reward Machines provide an automaton-inspired structure for specifying instructions, safety constraints, and other temporally extended reward-worthy behaviour. By exposing the underlying structure of a reward function, they enable the decomposition of an RL task, leading to impressive gains in sample efficiency.

We propose a novel preference modeling approach that utilizes AI feedback and only requires a small amount of human data.

In online advertising, for instance, the user's profile is the context, the

We study transfer learning for estimation in latent variable network models.

V arious dedicated algorithms have been recently proposed and studied by the machine-learning community. In contrast, active bipartite ranking rule is poorly documented in the literature. Due to its global nature, a strategy for labeling sequentially data points that are difficult to rank w.r.t. to the others is