BEE: Intervention-Adaptive Real-World Reinforcement Learning with Vision-Language-Action Models
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
The Flow has not summarised this story yet — read it at arXiv AI.
The paper presents Real‑Time EXPO‑FT, a reinforcement learning framework that fine‑tunes large Vision‑Language‑Action models for real‑time robotic control. It separates slow, expressive action generation from fast, reactive edits, allowing a lightweight policy to adjust actions based on the latest observation. Experiments on the Kinetix benchmark and four dynamic real‑world tasks show that Real‑Time EXPO‑FT achieves superior performance, improving policy success rates from 42% to 97% with only ten minutes of online data and no human intervention.
The paper introduces Adaptive Residual Correction (ARC), a lightweight post‑training module that adds a reinforcement‑learning–driven residual correction to a frozen imitation policy. ARC uses sparse human corrections to decide when the residual should activate, where in the residual action space to explore, and what the final residual action should be, thereby treating local failures as a localized learning problem rather than a global one. In experiments on three precision‑manipulation tasks, ARC raises average task success from 33.3 % to 75.0 % and confines the residual corrections to 2–3 dimensional subspaces that capture over 96 % of the correction magnitude. "whyItMatters":"The results demonstrate that sparse human guidance can effectively localize and constrain autonomous post‑training corrections, enabling significant performance gains without requiring full policy updates or dense human supervision."
The paper introduces PARTS, a real‑world subtask reinforcement learning framework that fine‑tunes a pretrained robot policy by focusing on critical bottleneck subtasks while keeping the base policy frozen. It uses agent‑generated selectors and success verifiers to provide local rewards, enabling learning even when full‑task successes are rare. Experiments on bimanual YAM and single‑arm Franka robots show that PARTS raises complete‑task success from 32% to 61% and from 50% to 95%, respectively, with only tens of minutes of real‑world RL rollouts and minimal human intervention.
arXiv:2605. 30226v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have emerged as a promising paradigm for grounding visual-language understanding into real-world robotic manipulation.
arXiv:2606. 27475v1 Announce Type: cross Abstract: Robots trained on real world data tend to be imprecise, slow, and brittle to perturbations.
arXiv:2606. 12372v1 Announce Type: cross Abstract: Human-in-the-loop reinforcement learning (HiL-RL) has emerged as an effective paradigm for real-world robotic manipulation, enabling online policy improvement with human guidance.