English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Guaranteeing safe behaviour of reinforcement learning (RL) policies posessignificant challenges for safety-critical applications, despite RL'sgenerality and scalability. To address this, we propose a new approach to applyverification methods from control theory to learned value functions. Byanalyzing task structures for safety preservation, we formalize originaltheorems that establish links between value functions and control barrierfunctions. Further, we propose novel metrics for verifying value functions insafe control tasks and practical implementation details to improve learning.Our work presents a novel method for certificate learning, which unlocks adiversity of verification techniques from control theory for RL policies, andmarks a significant step towards a formal framework for the general, scalable,and verifiable design of RL-based control systems. Code and videos areavailable at this https url: https://rl-cbf.github.io/

Value Functions are Control Barrier Functions: Verification of Safe Policies using Control Theory