arXiv AI July 20, 2026 By Jiaheng Hu, Peter Stone, Roberto Mart\'in-Mart\'in

SLAC: Safe and Efficient Real-Robot Reinforcement Learning via Unsupervised Simulation Pre-Training

arXiv:2506. 04147v5 Announce Type: replace-cross Abstract: Building capable household and industrial robots requires mastering the control of versatile, high-degree-of-freedom (DoF) systems such as mobile manipulators.

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 Machine Learning

Jun 29

Support-Constrained RL Enables Real-World Policy Improvement without Real-World Experience

arXiv:2606. 27475v1 Announce Type: cross Abstract: Robots trained on real world data tend to be imprecise, slow, and brittle to perturbations.

By Raymond Yu, William Huey, Mustafa Mukadam, Anusha Nagabandi, Abhishek Gupta

reinforcement-learning robotics efficiency

arXiv AI

Aug 19

EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models

EXPO-FT is a system that enables stable, sample‑efficient reinforcement learning fine‑tuning of pretrained Vision‑Language‑Action (VLA) policies. It achieves perfect success on a range of manipulation tasks—such as routing string lights, striking a pool ball, and inserting a flower into a wine bottle—using only about 19.1 minutes of online robot data. The approach outperforms both RL-from-scratch and existing VLA fine‑tuning methods, and the authors provide an open‑source codebase to support wider adoption.

By Perry Dong, Kuo-Han Hung, Tian Gao, Dorsa Sadigh, Chelsea Finn

reinforcement-learning robotics fine-tuning multimodal

arXiv Machine Learning

Sep 17

Reinforcement Learning for Real-Time Vision-Language-Action Policies

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.

By Perry Dong, Kuo-Han Hung, Dorsa Sadigh, Chelsea Finn

reinforcement-learning robotics fine-tuning efficiency multimodal benchmarks

arXiv AI

Jun 11

LUCID: Learning Embodiment-Agnostic Intent Models from Unstructured Human Videos for Scalable Dexterous Robot Skill Acquisition

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.

By Harsh Gupta, Guanya Shi, Wenzhen Yuan

robotics

arXiv Machine Learning

Aug 13

Adaptation of Generalist Robot Policies with Minimal Data

arXiv:2608. 11363v1 Announce Type: cross Abstract: A central goal in robot learning is to move beyond task-specific human data collection toward robots that improve through autonomous interaction.

By Shreyas Kowshik, Sreyas Venkataraman, Leo Wang, Niharika Pant, Max Simchowitz, Aviral Kumar

agents reinforcement-learning robotics

arXiv AI

Jun 2

SpeedAug: Policy Acceleration via Tempo-Enriched Policy and RL Fine-Tuning

arXiv:2512. 00062v2 Announce Type: replace-cross Abstract: Robotic policy learning for complex real-world manipulation tasks has seen rapid recent progress, enabled in large part by the ability to collect demonstrations through human operation.

By Taewook Nam, Junmo Cho, Youngsoo Jang, Sung Ju Hwang

reinforcement-learning robotics fine-tuning efficiency benchmarks

One email a morning, machine-written

Related stories

Support-Constrained RL Enables Real-World Policy Improvement without Real-World Experience

EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models

Reinforcement Learning for Real-Time Vision-Language-Action Policies

LUCID: Learning Embodiment-Agnostic Intent Models from Unstructured Human Videos for Scalable Dexterous Robot Skill Acquisition

Adaptation of Generalist Robot Policies with Minimal Data

SpeedAug: Policy Acceleration via Tempo-Enriched Policy and RL Fine-Tuning