Likun Wang

Enhanced DACER Algorithm with High Diffusion Efficiency

Mind Your Entropy: From Maximum Entropy to Trajectory Entropy-Constrained RL

FAME : Factor-aware Mixture-of-Experts with Pretrained Encoder for combinatorial generalization

ODE-based Smoothing Neural Network for Reinforcement Learning Tasks

Bootstrap Off-policy with World Model

Off-policy Reinforcement Learning with Model-based Exploration Augmentation