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 is a promising approach to synthesizing policies forchallenging robotics tasks. A key problem is how to ensure safety of thelearned policy---e.g., that a walking robot does not fall over or that anautonomous car does not run into an obstacle. We focus on the setting where thedynamics are known, and the goal is to ensure that a policy trained insimulation satisfies a given safety constraint. We propose an approach, calledmodel predictive shielding (MPS), that switches on-the-fly between a learnedpolicy and a backup policy to ensure safety. We prove that our approachguarantees safety, and empirically evaluate it on the cart-pole.

Safe Reinforcement Learning with Nonlinear Dynamics via Model Predictive Shielding