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

Deep Reinforcement Learning (RL) has shown promise in addressing complexrobotic challenges. In real-world applications, RL is often accompanied byfailsafe controllers as a last resort to avoid catastrophic events. Whilenecessary for safety, these interventions can result in undesirable behaviors,such as abrupt braking or aggressive steering. This paper proposes two safetyintervention reduction methods: proactive replacement and proactive projection,which change the action of the agent if it leads to a potential failsafeintervention. These approaches are compared to state-of-the-art constrained RLon the OpenAI safety gym benchmark and a human-robot collaboration task. Ourstudy demonstrates that the combination of our method with provably safe RLleads to high-performing policies with zero safety violations and a low numberof failsafe interventions. Our versatile method can be applied to a wide rangeof real-world robotic tasks, while effectively improving safety withoutsacrificing task performance.

Reducing Safety Interventions in Provably Safe Reinforcement Learning