Qing-Shan Jia

Reinforcement Learning (4) Methods (4) Deep Learning (1) Machine Learning (1) Mathematics & Optimization (1) Applications (1) Learning Types · Machine Learning (1) Learning Types · Deep Learning (1) Optimization (1)

query selection (2) preference-based reinforcement learning (2) policy optimization (1) distribution matching (1) bilevel optimization (1) human feedback (1) reward model (1) skill learning (1) robotics manipulation (1) experience replay (1) reward signal (1) trajectory embedding (1) reward correction (1) pessimistic reinforcement learning (1) ambiguous feedback (1) human preference comparisons (1) offline pbrl (1) contrastive learning (1) preference reinforcement learning (1) offline reinforcement learning (1)