5 papers · 1 filter
Beyond Policy Patches: Distilling RL Specialists into Vision-Language-Action Policies
Zhennan Jiang, Tingying Xie, Shilong Ji +11
Vision-language-action (VLA) policies can handle noncritical stages of long-horizon manipulation yet fail during short precision-critical phases. Lightweight reinforcement learning…
USER: A Unified and Extensible System for Real-World Online Policy Learning in Embodied AI
Hongzhi Zang, Shu'ang Yu, Hao Lin +14
Online policy learning directly in the physical world is a promising yet challenging direction for embodied intelligence. Unlike simulation, real-world systems cannot be arbitraril…
RoboScape-R: Unified Reward-Observation World Models for Generalizable Robotics Training via RL
Yinzhou Tang, Yu Shang, Yinuo Chen +8
Achieving generalizable embodied policies remains a key challenge. Traditional policy learning paradigms, including both Imitation Learning (IL) and Reinforcement Learning (RL), st…
SAC Flow: Sample-Efficient Reinforcement Learning of Flow-Based Policies via Velocity-Reparameterized Sequential Modeling
Yixian Zhang, Shu'ang Yu, Tonghe Zhang +6
Training expressive flow-based policies with off-policy reinforcement learning is notoriously unstable due to gradient pathologies in the multi-step action sampling process. We tra…
JuggleRL: Mastering Ball Juggling with a Quadrotor via Deep Reinforcement Learning
Shilong Ji, Yinuo Chen, Chuqi Wang +9
Aerial robots interacting with objects must perform precise, contact-rich maneuvers under uncertainty. In this paper, we study the problem of aerial ball juggling using a quadrotor…