Houqiang Li

Latest

• State Sequences Prediction via Fourier Transform for Representation Learning (Spotlight)
• Learning Robust Policy against Disturbance in Transition Dynamics via State-Conservative Policy Optimization
• Sample-Efficient Reinforcement Learning via Conservative Model-Based Actor-Critic
• Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking
• Promoting Stochasticity for Expressive Policies via a Simple and Efficient Regularization Method
• Deep Model-Based Reinforcement Learning via Estimated Uncertainty and Conservative Policy Optimization