Ping Luo

Latest

• Decomposed Mutual Information Optimization for Generalized Context in Meta-Reinforcement Learning
• Flow-based Recurrent Belief State Learning for POMDPs
• CtrlFormer: Learning Transferable State Representation for Visual Control via Transformer
• Scale-Equivalent Distillation for Semi-Supervised Object Detection
• Model-Based Reinforcement Learning via Imagination with Derived Memory