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) has demonstrated impressive performance invarious areas such as video games and robotics. However, ensuring safety andstability, which are two critical properties from a control perspective,remains a significant challenge when using RL to control real-world systems. Inthis paper, we first provide definitions of safety and stability for the RLsystem, and then combine the control barrier function (CBF) and controlLyapunov function (CLF) methods with the actor-critic method in RL to propose aBarrier-Lyapunov Actor-Critic (BLAC) framework which helps maintain theaforementioned safety and stability for the system. In this framework, CBFconstraints for safety and CLF constraint for stability are constructed basedon the data sampled from the replay buffer, and the augmented Lagrangian methodis used to update the parameters of the RL-based controller. Furthermore, anadditional backup controller is introduced in case the RL-based controllercannot provide valid control signals when safety and stability constraintscannot be satisfied simultaneously. Simulation results show that this frameworkyields a controller that can help the system approach the desired state andcause fewer violations of safety constraints compared to baseline algorithms.

Stable and Safe Reinforcement Learning via a Barrier-Lyapunov Actor-Critic Approach