Matches in SemOpenAlex for { <https://semopenalex.org/work/W3065457986> ?p ?o ?g. }
- W3065457986 abstract "As the operations of autonomous systems generally affect simultaneously several users, it is crucial that their designs account for fairness considerations. In contrast to standard (deep) reinforcement learning (RL), we investigate the problem of learning a policy that treats its users equitably. In this paper, we formulate this novel RL problem, in which an objective function, which encodes a notion of fairness that we formally define, is optimized. For this problem, we provide a theoretical discussion where we examine the case of discounted rewards and that of average rewards. During this analysis, we notably derive a new result in the standard RL setting, which is of independent interest: it states a novel bound on the approximation error with respect to the optimal average reward of that of a policy optimal for the discounted reward. Since learning with discounted rewards is generally easier, this discussion further justifies finding a fair policy for the average reward by learning a fair policy for the discounted reward. Thus, we describe how several classic deep RL algorithms can be adapted to our fair optimization problem, and we validate our approach with extensive experiments in three different domains." @default.
- W3065457986 created "2020-08-24" @default.
- W3065457986 creator A5028712584 @default.
- W3065457986 creator A5029379398 @default.
- W3065457986 creator A5073106112 @default.
- W3065457986 date "2020-08-18" @default.
- W3065457986 modified "2023-09-27" @default.
- W3065457986 title "Learning Fair Policies in Multiobjective (Deep) Reinforcement Learning with Average and Discounted Rewards" @default.
- W3065457986 cites W1050019105 @default.
- W3065457986 cites W1501015851 @default.
- W3065457986 cites W1518931405 @default.
- W3065457986 cites W1521563520 @default.
- W3065457986 cites W1538380038 @default.
- W3065457986 cites W1606011487 @default.
- W3065457986 cites W1850488217 @default.
- W3065457986 cites W1967037758 @default.
- W3065457986 cites W1979765269 @default.
- W3065457986 cites W2001302314 @default.
- W3065457986 cites W2011481463 @default.
- W3065457986 cites W2034168406 @default.
- W3065457986 cites W2098584016 @default.
- W3065457986 cites W2117518378 @default.
- W3065457986 cites W2119567691 @default.
- W3065457986 cites W2144681685 @default.
- W3065457986 cites W2145339207 @default.
- W3065457986 cites W2150912223 @default.
- W3065457986 cites W2155027007 @default.
- W3065457986 cites W2401796785 @default.
- W3065457986 cites W2736601468 @default.
- W3065457986 cites W2765607800 @default.
- W3065457986 cites W2766447205 @default.
- W3065457986 cites W2794791586 @default.
- W3065457986 cites W2905677277 @default.
- W3065457986 cites W2963236854 @default.
- W3065457986 cites W2963327716 @default.
- W3065457986 cites W2963422834 @default.
- W3065457986 cites W2963455877 @default.
- W3065457986 cites W2964043796 @default.
- W3065457986 cites W2964063980 @default.
- W3065457986 cites W2970727184 @default.
- W3065457986 cites W2990118529 @default.
- W3065457986 cites W3106076062 @default.
- W3065457986 cites W3140214885 @default.
- W3065457986 cites W50296447 @default.
- W3065457986 hasPublicationYear "2020" @default.
- W3065457986 type Work @default.
- W3065457986 sameAs 3065457986 @default.
- W3065457986 citedByCount "0" @default.
- W3065457986 crossrefType "posted-content" @default.
- W3065457986 hasAuthorship W3065457986A5028712584 @default.
- W3065457986 hasAuthorship W3065457986A5029379398 @default.
- W3065457986 hasAuthorship W3065457986A5073106112 @default.
- W3065457986 hasConcept C126255220 @default.
- W3065457986 hasConcept C14036430 @default.
- W3065457986 hasConcept C14646407 @default.
- W3065457986 hasConcept C154945302 @default.
- W3065457986 hasConcept C188116033 @default.
- W3065457986 hasConcept C2776502983 @default.
- W3065457986 hasConcept C33923547 @default.
- W3065457986 hasConcept C41008148 @default.
- W3065457986 hasConcept C78458016 @default.
- W3065457986 hasConcept C86803240 @default.
- W3065457986 hasConcept C97541855 @default.
- W3065457986 hasConceptScore W3065457986C126255220 @default.
- W3065457986 hasConceptScore W3065457986C14036430 @default.
- W3065457986 hasConceptScore W3065457986C14646407 @default.
- W3065457986 hasConceptScore W3065457986C154945302 @default.
- W3065457986 hasConceptScore W3065457986C188116033 @default.
- W3065457986 hasConceptScore W3065457986C2776502983 @default.
- W3065457986 hasConceptScore W3065457986C33923547 @default.
- W3065457986 hasConceptScore W3065457986C41008148 @default.
- W3065457986 hasConceptScore W3065457986C78458016 @default.
- W3065457986 hasConceptScore W3065457986C86803240 @default.
- W3065457986 hasConceptScore W3065457986C97541855 @default.
- W3065457986 hasLocation W30654579861 @default.
- W3065457986 hasOpenAccess W3065457986 @default.
- W3065457986 hasPrimaryLocation W30654579861 @default.
- W3065457986 hasRelatedWork W1802827359 @default.
- W3065457986 hasRelatedWork W1975946549 @default.
- W3065457986 hasRelatedWork W1998649829 @default.
- W3065457986 hasRelatedWork W2002894942 @default.
- W3065457986 hasRelatedWork W2593425276 @default.
- W3065457986 hasRelatedWork W2611974834 @default.
- W3065457986 hasRelatedWork W2799811007 @default.
- W3065457986 hasRelatedWork W2960103027 @default.
- W3065457986 hasRelatedWork W3007560180 @default.
- W3065457986 hasRelatedWork W3016149195 @default.
- W3065457986 hasRelatedWork W3035432460 @default.
- W3065457986 hasRelatedWork W3037141151 @default.
- W3065457986 hasRelatedWork W3038092671 @default.
- W3065457986 hasRelatedWork W3094431185 @default.
- W3065457986 hasRelatedWork W3095229480 @default.
- W3065457986 hasRelatedWork W3099551617 @default.
- W3065457986 hasRelatedWork W3102824929 @default.
- W3065457986 hasRelatedWork W3124233287 @default.
- W3065457986 hasRelatedWork W3126592918 @default.
- W3065457986 hasRelatedWork W3205955747 @default.
- W3065457986 isParatext "false" @default.
- W3065457986 isRetracted "false" @default.
- W3065457986 magId "3065457986" @default.