Matches in SemOpenAlex for { <https://semopenalex.org/work/W2593670774> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W2593670774 abstract "We initiate the study of fairness in reinforcement learning, where the actions of a learning algorithm may affect its environment and future rewards. Our fairness constraint requires that an algorithm never prefers one action over another if the long-term (discounted) reward of choosing the latter action is higher. Our first result is negative: despite the fact that fairness is consistent with the optimal policy, any learning algorithm satisfying fairness must take time exponential in the number of states to achieve non-trivial approximation to the optimal policy. We then provide a provably fair polynomial time algorithm under an approximate notion of fairness, thus establishing an exponential gap between exact and approximate fairness" @default.
- W2593670774 created "2017-03-16" @default.
- W2593670774 creator A5019181561 @default.
- W2593670774 creator A5024878679 @default.
- W2593670774 creator A5037449825 @default.
- W2593670774 creator A5045592180 @default.
- W2593670774 creator A5057693522 @default.
- W2593670774 date "2016-11-09" @default.
- W2593670774 modified "2023-09-25" @default.
- W2593670774 title "Fairness in Reinforcement Learning" @default.
- W2593670774 cites W1515851193 @default.
- W2593670774 cites W183455186 @default.
- W2593670774 cites W2014352947 @default.
- W2593670774 cites W2026019770 @default.
- W2593670774 cites W2059141064 @default.
- W2593670774 cites W2095932468 @default.
- W2593670774 cites W2100960835 @default.
- W2593670774 cites W2136503687 @default.
- W2593670774 cites W2161521419 @default.
- W2593670774 cites W2162670686 @default.
- W2593670774 cites W2396394641 @default.
- W2593670774 cites W2524301210 @default.
- W2593670774 cites W2542213270 @default.
- W2593670774 cites W2594166818 @default.
- W2593670774 cites W2953389312 @default.
- W2593670774 hasPublicationYear "2016" @default.
- W2593670774 type Work @default.
- W2593670774 sameAs 2593670774 @default.
- W2593670774 citedByCount "6" @default.
- W2593670774 countsByYear W25936707742017 @default.
- W2593670774 countsByYear W25936707742018 @default.
- W2593670774 countsByYear W25936707742019 @default.
- W2593670774 countsByYear W25936707742020 @default.
- W2593670774 crossrefType "posted-content" @default.
- W2593670774 hasAuthorship W2593670774A5019181561 @default.
- W2593670774 hasAuthorship W2593670774A5024878679 @default.
- W2593670774 hasAuthorship W2593670774A5037449825 @default.
- W2593670774 hasAuthorship W2593670774A5045592180 @default.
- W2593670774 hasAuthorship W2593670774A5057693522 @default.
- W2593670774 hasConcept C11867375 @default.
- W2593670774 hasConcept C121332964 @default.
- W2593670774 hasConcept C126255220 @default.
- W2593670774 hasConcept C134306372 @default.
- W2593670774 hasConcept C151376022 @default.
- W2593670774 hasConcept C154945302 @default.
- W2593670774 hasConcept C157764524 @default.
- W2593670774 hasConcept C2524010 @default.
- W2593670774 hasConcept C2776036281 @default.
- W2593670774 hasConcept C2780791683 @default.
- W2593670774 hasConcept C33923547 @default.
- W2593670774 hasConcept C41008148 @default.
- W2593670774 hasConcept C555944384 @default.
- W2593670774 hasConcept C61797465 @default.
- W2593670774 hasConcept C62520636 @default.
- W2593670774 hasConcept C76155785 @default.
- W2593670774 hasConcept C97541855 @default.
- W2593670774 hasConceptScore W2593670774C11867375 @default.
- W2593670774 hasConceptScore W2593670774C121332964 @default.
- W2593670774 hasConceptScore W2593670774C126255220 @default.
- W2593670774 hasConceptScore W2593670774C134306372 @default.
- W2593670774 hasConceptScore W2593670774C151376022 @default.
- W2593670774 hasConceptScore W2593670774C154945302 @default.
- W2593670774 hasConceptScore W2593670774C157764524 @default.
- W2593670774 hasConceptScore W2593670774C2524010 @default.
- W2593670774 hasConceptScore W2593670774C2776036281 @default.
- W2593670774 hasConceptScore W2593670774C2780791683 @default.
- W2593670774 hasConceptScore W2593670774C33923547 @default.
- W2593670774 hasConceptScore W2593670774C41008148 @default.
- W2593670774 hasConceptScore W2593670774C555944384 @default.
- W2593670774 hasConceptScore W2593670774C61797465 @default.
- W2593670774 hasConceptScore W2593670774C62520636 @default.
- W2593670774 hasConceptScore W2593670774C76155785 @default.
- W2593670774 hasConceptScore W2593670774C97541855 @default.
- W2593670774 hasOpenAccess W2593670774 @default.
- W2593670774 hasRelatedWork W13019891 @default.
- W2593670774 hasRelatedWork W1482986274 @default.
- W2593670774 hasRelatedWork W1515673225 @default.
- W2593670774 hasRelatedWork W1573284616 @default.
- W2593670774 hasRelatedWork W1748461940 @default.
- W2593670774 hasRelatedWork W1771839501 @default.
- W2593670774 hasRelatedWork W1977973340 @default.
- W2593670774 hasRelatedWork W2100960835 @default.
- W2593670774 hasRelatedWork W2118977012 @default.
- W2593670774 hasRelatedWork W2147228966 @default.
- W2593670774 hasRelatedWork W2629221296 @default.
- W2593670774 hasRelatedWork W2945725195 @default.
- W2593670774 hasRelatedWork W2963449662 @default.
- W2593670774 hasRelatedWork W2963771282 @default.
- W2593670774 hasRelatedWork W3002671839 @default.
- W2593670774 hasRelatedWork W3005538141 @default.
- W2593670774 hasRelatedWork W3142278306 @default.
- W2593670774 hasRelatedWork W3163180484 @default.
- W2593670774 hasRelatedWork W42168290 @default.
- W2593670774 hasRelatedWork W2182962113 @default.
- W2593670774 isParatext "false" @default.
- W2593670774 isRetracted "false" @default.
- W2593670774 magId "2593670774" @default.
- W2593670774 workType "article" @default.