← Back to all news
arXiv AI By Shaekh Mohammad Shithil, Lantao Liu

SEVI: Safe Evidential Real-World Reinforcement Learning

Read the original on arXiv AI →

SEVI (Safe Evidential Real-World Reinforcement Learning) is a framework that adds a safety intervention layer to real‑world policy learning. It uses an Evidential Safety Critic to estimate both future constraint‑violation risk and epistemic uncertainty in a single forward pass, and overrides unsafe or poorly supported actions with an offline‑trained recovery policy. Experiments on simulated manipulation tasks and a real‑world USB insertion task show that SEVI improves trajectory‑level safety prediction, task success, and reduces unsafe events by 13.4–57.1% compared to other safe RL baselines.

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.

Related stories

arXiv AI
Sep 24

Turning Safety into Competence: Minimally Exploitable Robot Policies via Safety-Filtered Reinforcement Learning

The paper introduces Safety to Competence (S2C), a two‑stage reinforcement learning framework that first learns a safety filter and then trains a competitive task policy while embedding the filter. By separating safety synthesis from task learning, S2C reduces training complexity and prevents the policy from being exploited by adversarial attacks. Experiments on simulated touchdown games show that S2C achieves higher win rates, better Elo ratings, and lower exploitability than eight safe‑RL baselines, and hardware tests confirm its competence against a human opponent.

By Ruihan Wu, Rui Yang, Donggeon David Oh, Duy Nguyen, Haimin Hu
reinforcement-learningroboticssafety
More like this →
arXiv Machine Learning
5d ago

RBGA: Residual-Budget Guide Arbitration for Offline-to-Online Safe Reinforcement Learning in Dexterous Manipulation

The paper introduces RBGA, an algorithm for offline-to-online safe reinforcement learning in dexterous manipulation. RBGA tracks the remaining safety budget during an episode and uses it to arbitrate between offline guidance and an evolving online policy, comparing cost-to-go estimates at each step. The authors provide theoretical analysis of safety implications and demonstrate through experiments that RBGA improves online policy performance while preserving safety.

By Zongyou Yu, Ao Zhou, Xiongbo Shi, Jiayi Guan, Shihang Du, Xudong Zhang, Shangding Gu, Junqiao Zhao, Hanli Wang, Guang Chen
reinforcement-learningroboticssafety
More like this →