Xuening Feng

active learning (1) reinforcement learning (1) epistemic uncertainty (1) reinforcement learning from human feedback (1) query selection (1) reward function (1) first-order logic (1) human feedback (1) pairwise comparison (1) interpretable model (1) reward function learning (1) inductive logic programming (1) first-order rule (1) query generation (1) rule induction (1) neuro-symbolic model (1)