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

Prior work on safe Reinforcement Learning (RL) has studied risk-aversion torandomness in dynamics (aleatory) and to model uncertainty (epistemic) inisolation. We propose and analyze a new framework to jointly model the riskassociated with epistemic and aleatory uncertainties in finite-horizon anddiscounted infinite-horizon MDPs. We call this framework that combinesRisk-Averse and Soft-Robust methods RASR. We show that when the risk-aversionis defined using either EVaR or the entropic risk, the optimal policy in RASRcan be computed efficiently using a new dynamic program formulation with atime-dependent risk level. As a result, the optimal risk-averse policies aredeterministic but time-dependent, even in the infinite-horizon discountedsetting. We also show that particular RASR objectives reduce to risk-averse RLwith mean posterior transition probabilities. Our empirical results show thatour new algorithms consistently mitigate uncertainty as measured by EVaR andother standard risk measures.

RASR: Risk-Averse Soft-Robust MDPs with EVaR and Entropic Risk