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

As the operations of autonomous systems generally affect simultaneouslyseveral users, it is crucial that their designs account for fairnessconsiderations. In contrast to standard (deep) reinforcement learning (RL), weinvestigate the problem of learning a policy that treats its users equitably.In this paper, we formulate this novel RL problem, in which an objectivefunction, which encodes a notion of fairness that we formally define, isoptimized. For this problem, we provide a theoretical discussion where weexamine the case of discounted rewards and that of average rewards. During thisanalysis, we notably derive a new result in the standard RL setting, which isof independent interest: it states a novel bound on the approximation errorwith respect to the optimal average reward of that of a policy optimal for thediscounted reward. Since learning with discounted rewards is generally easier,this discussion further justifies finding a fair policy for the average rewardby learning a fair policy for the discounted reward. Thus, we describe howseveral classic deep RL algorithms can be adapted to our fair optimizationproblem, and we validate our approach with extensive experiments in threedifferent domains.

Learning Fair Policies in Multiobjective (Deep) Reinforcement Learning with Average and Discounted Rewards