Katherine Metcalf

policy learning (2) preference-based reinforcement learning (2) representation learning (2) hierarchical learning (1) out-of-distribution generalization (1) direct preference optimization (1) embedding space (1) human feedback (1) language model alignment (1) parameter-efficient learning (1) temporal abstraction (1) cross-lingual alignment (1) reinforcement learning from human feedback (1) parameter efficient (1) reward function (1) self-supervised learning (1) sample efficiency (1) generalization capability (1) reward model (1) deep reinforcement learning (1)