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

Reinforcement learning (RL) is an area of significant research interest, andsafe RL in particular is attracting attention due to its ability to handlesafety-driven constraints that are crucial for real-world applications. Thiswork proposes a novel approach to RL training, called control invariant set(CIS) enhanced RL, which leverages the advantages of utilizing the explicitform of CIS to improve stability guarantees and sampling efficiency.Furthermore, the robustness of the proposed approach is investigated in thepresence of uncertainty. The approach consists of two learning stages: offlineand online. In the offline stage, CIS is incorporated into the reward design,initial state sampling, and state reset procedures. This incorporation of CISfacilitates improved sampling efficiency during the offline training process.In the online stage, RL is retrained whenever the predicted next step state isoutside of the CIS, which serves as a stability criterion, by introducing aSafety Supervisor to examine the safety of the action and make necessarycorrections. The stability analysis is conducted for both cases, with andwithout uncertainty. To evaluate the proposed approach, we apply it to asimulated chemical reactor. The results show a significant improvement insampling efficiency during offline training and closed-loop stability guaranteein the online implementation, with and without uncertainty.

Control invariant set enhanced safe reinforcement learning: improved sampling efficiency, guaranteed stability and robustness