Guojian Zhan

Mean Flow Policy with Instantaneous Velocity Constraint for One-step Action Generation

Harmonic Constrained Reinforcement Learning

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

Enhanced DACER Algorithm with High Diffusion Efficiency

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

Bootstrap Off-policy with World Model

Off-policy Reinforcement Learning with Model-based Exploration Augmentation