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

Safe reinforcement learning (RL) aims to satisfy safety constraints duringtraining. However, guaranteeing safety during training remained a challengingproblem. This paper presents a novel framework that integrates Backup ControlBarrier Functions (BCBFs) with reinforcement learning (RL) to enable safeexploration called RLBUS: Reinforcement Learning Backup Shield. BCBFsincorporate backup controllers that predict a system's finite-time response,facilitating online optimization of a control policy that maintains the forwardinvariance of a safe subset, while satisfying actuator constraints. Building onthe soft-minimum/soft-maximum CBF method from prior work, which ensuresfeasibility and continuity of the BCBF with multiple backup controllers, thispaper proposes integrating these BCBFs with RL. This framework leverages RL tolearn a better backup policy to enlarge the forward invariant set, whileguaranteeing safety during training. By combining backup controllers and RL,the approach provides safety and feasibility guarantees during training andenables safe online exploration with zero training-time safety violations. Themethod is demonstrated on an inverted pendulum example, where expanding theforward invariant set through RL allows the pendulum to safely explore largerregions of state space.

Safe Exploration in Reinforcement Learning: Training Backup Control Barrier Functions with Zero Training Time Safety Violations