Yixian Zhang

Policy Newton Algorithm in Reproducing Kernel Hilbert Space

SAC Flow: Sample-Efficient Reinforcement Learning of Flow-Based Policies via Velocity-Reparameterized Sequential Modeling

SKARL: Provably Scalable Kernel Mean Field Reinforcement Learning for Variable-Size Multi-Agent Systems

Residual Kernel Policy Network: Enhancing Stability and Robustness in RKHS-Based Reinforcement Learning