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/

Zendy Pro

Presents the zaia usage as premium feature

ZAIA

Presents AI Discovery search usage as a premium feature

AI Discovery

Presents AI Discovery explain and summary usage as a premium feature

Content Analysis

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Presents the pdf analysis as premium feature

PDF Analysis

1500 Top-up

3000 Top-up

Zendy Basic

2500 Top-up

Zendy Unlimited

Presents the access of premium content as premium feature

Premium Content

Safe and optimal controller synthesis for switched-controlled hybrid systems,which combine differential equations and discrete changes of the system'sstate, is known to be intricately hard. Reinforcement learning has beenleveraged to construct near-optimal controllers, but their behavior is notguaranteed to be safe, even when it is encouraged by reward engineering. Oneway of imposing safety to a learned controller is to use a shield, which iscorrect by design. However, obtaining a shield for non-linear and hybridenvironments is itself intractable. In this paper, we propose the constructionof a shield using the so-called barbaric method, where an approximate finiterepresentation of an underlying partition-based two-player safety game isextracted via systematically picked samples of the true transition function.While hard safety guarantees are out of reach, we experimentally demonstratestrong statistical safety guarantees with a prototype implementation and UPPAALSTRATEGO. Furthermore, we study the impact of the synthesized shield whenapplied as either a pre-shield (applied before learning a controller) or apost-shield (only applied after learning a controller). We experimentallydemonstrate superiority of the pre-shielding approach. We apply our techniqueon a range of case studies, including two industrial examples, and furtherstudy post-optimization of the post-shielding approach.

Shielded Reinforcement Learning for Hybrid Systems