SAC Flow: Sample-Efficient Reinforcement Learning of Flow-Based Policies via Velocity-Reparameterized Sequential Modeling Paper • 2509.25756 • Published Sep 30, 2025
JuggleRL: Mastering Ball Juggling with a Quadrotor via Deep Reinforcement Learning Paper • 2509.24892 • Published Sep 29, 2025
RLinf-USER: A Unified and Extensible System for Real-World Online Policy Learning in Embodied AI Paper • 2602.07837 • Published Feb 8 • 57
