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

We consider risk-averse learning in repeated unknown games where the goal ofthe agents is to minimize their individual risk of incurring significantly highcost. Specifically, the agents use the conditional value at risk (CVaR) as arisk measure and rely on bandit feedback in the form of the cost values of theselected actions at every episode to estimate their CVaR values and updatetheir actions. A major challenge in using bandit feedback to estimate CVaR isthat the agents can only access their own cost values, which, however, dependon the actions of all agents. To address this challenge, we propose a newrisk-averse learning algorithm with momentum that utilizes the full historicalinformation on the cost values. We show that this algorithm achieves sub-linearregret and matches the best known algorithms in the literature. We providenumerical experiments for a Cournot game that show that our method outperformsexisting methods.

A Zeroth-Order Momentum Method for Risk-Averse Online Convex Games