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

Many real-world domains require safe decision making in uncertainenvironments. In this work, we introduce a deep reinforcement learningframework for approaching this important problem. We consider a distributionover transition models, and apply a risk-averse perspective towards modeluncertainty through the use of coherent distortion risk measures. We providerobustness guarantees for this framework by showing it is equivalent to aspecific class of distributionally robust safe reinforcement learning problems.Unlike existing approaches to robustness in deep reinforcement learning,however, our formulation does not involve minimax optimization. This leads toan efficient, model-free implementation of our approach that only requiresstandard data collection from a single training environment. In experiments oncontinuous control tasks with safety constraints, we demonstrate that ourframework produces robust performance and safety at deployment time across arange of perturbed test environments.

Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learning