arXiv:2606. 18594v1 Announce Type: cross Abstract: In real-world reinforcement learning (RL), the choice of action space can play a key role in shaping motion smoothness, safety, and overall task performance.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
arXiv:2609.38059v1 Announce Type: cross Abstract: Real-world robot learning is constrained by the cost of collecting experience and evaluating candidate behaviors. Video generation models offer a sca...
arXiv:2603. 22876v2 Announce Type: replace-cross Abstract: Learning a generalist control policy for robotic manipulation typically relies on large-scale datasets.
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.
arXiv:2602. 13197v2 Announce Type: replace-cross Abstract: The ability to learn manipulation skills by watching videos of humans has the potential to unlock a new source of highly scalable data for robot learning.
arXiv:2505. 03296v2 Announce Type: replace-cross Abstract: We present Mixture of Discrete-time Gaussian Processes (MiDiGap), a novel approach for flexible policy representation and imitation learning in robot manipulation.
arXiv:2606. 11628v1 Announce Type: cross Abstract: The most widely-adopted robot learning pipelines today learn skills from robot demonstrations or structured human data, which are expensive to collect and tied to specific embodiments.