Minghui Zhu

Leveraging Explanation to Improve Generalization of Meta Reinforcement Learning

A Constrained Bi-level Optimization Framework for Constrained Reinforcement Learning from Human Feedback

Inverse Reinforcement Learning of Interactive Scenarios

Explainable Reinforcement Learning from Human Feedback to Improve Alignment

UTILITY: Utilizing Explainable Reinforcement Learning to Improve Reinforcement Learning

Efficient Safe Meta-Reinforcement Learning: Provable Near-Optimality and Anytime Safety

Meta-Reinforcement Learning with Adaptation from Human Feedback via Preference-Order-Preserving Task Embedding

Safe Meta-Reinforcement Learning via Dual-Method-Based Policy Adaptation: Near-Optimality and Anytime Safety Guarantee

Learn from Interactions: General-Sum Interactive Inverse Reinforcement Learning

Improving Generalization of Meta Reinforcement Learning via Explanation