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

The usage of automated learning agents is becoming increasingly prevalent inmany online economic applications such as online auctions and automatedtrading. Motivated by such applications, this paper is dedicated to fundamentalmodeling and analysis of the strategic situations that the users of automatedlearning agents are facing. We consider strategic settings where several usersengage in a repeated online interaction, assisted by regret-minimizing learningagents that repeatedly play a "game" on their behalf. We propose to view theoutcomes of the agents' dynamics as inducing a "meta-game" between the users.Our main focus is on whether users can benefit in this meta-game from"manipulating" their own agents by misreporting their parameters to them. Wedefine a general framework to model and analyze these strategic interactionsbetween users of learning agents for general games and analyze the equilibriainduced between the users in three classes of games. We show that, generally,users have incentives to misreport their parameters to their own agents, andthat such strategic user behavior can lead to very different outcomes thanthose anticipated by standard analysis.

How and Why to Manipulate Your Own Agent: On the Incentives of Users of Learning Agents