Matches in SemOpenAlex for { <https://semopenalex.org/work/W166795445> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W166795445 abstract "We study online learning of finite Markov decision process (MDP) problems when a side information vector is available. The problem is motivated by applications such as clinical trials, recommendation systems, etc. Such applications have an episodic structure, where each episode corresponds to a patient/customer. Our objective is to compete with the optimal dynamic policy that can take side information into account. We propose a computationally efficient algorithm and show that its regret is at most $O(sqrt{T})$, where $T$ is the number of rounds. To best of our knowledge, this is the first regret bound for this setting." @default.
- W166795445 created "2016-06-24" @default.
- W166795445 creator A5047010941 @default.
- W166795445 creator A5077167635 @default.
- W166795445 date "2014-06-26" @default.
- W166795445 modified "2023-09-29" @default.
- W166795445 title "Online learning in MDPs with side information" @default.
- W166795445 cites W1850488217 @default.
- W166795445 cites W2075268401 @default.
- W166795445 cites W2100677568 @default.
- W166795445 cites W2135829225 @default.
- W166795445 cites W2168405694 @default.
- W166795445 cites W2241126168 @default.
- W166795445 cites W2491144192 @default.
- W166795445 cites W50486269 @default.
- W166795445 cites W53582479 @default.
- W166795445 hasPublicationYear "2014" @default.
- W166795445 type Work @default.
- W166795445 sameAs 166795445 @default.
- W166795445 citedByCount "7" @default.
- W166795445 countsByYear W1667954452016 @default.
- W166795445 countsByYear W1667954452017 @default.
- W166795445 countsByYear W1667954452018 @default.
- W166795445 countsByYear W1667954452019 @default.
- W166795445 countsByYear W1667954452021 @default.
- W166795445 crossrefType "posted-content" @default.
- W166795445 hasAuthorship W166795445A5047010941 @default.
- W166795445 hasAuthorship W166795445A5077167635 @default.
- W166795445 hasConcept C105795698 @default.
- W166795445 hasConcept C106189395 @default.
- W166795445 hasConcept C119857082 @default.
- W166795445 hasConcept C126255220 @default.
- W166795445 hasConcept C136764020 @default.
- W166795445 hasConcept C154945302 @default.
- W166795445 hasConcept C159886148 @default.
- W166795445 hasConcept C199360897 @default.
- W166795445 hasConcept C2986087404 @default.
- W166795445 hasConcept C33923547 @default.
- W166795445 hasConcept C3454156 @default.
- W166795445 hasConcept C41008148 @default.
- W166795445 hasConcept C50817715 @default.
- W166795445 hasConcept C98763669 @default.
- W166795445 hasConceptScore W166795445C105795698 @default.
- W166795445 hasConceptScore W166795445C106189395 @default.
- W166795445 hasConceptScore W166795445C119857082 @default.
- W166795445 hasConceptScore W166795445C126255220 @default.
- W166795445 hasConceptScore W166795445C136764020 @default.
- W166795445 hasConceptScore W166795445C154945302 @default.
- W166795445 hasConceptScore W166795445C159886148 @default.
- W166795445 hasConceptScore W166795445C199360897 @default.
- W166795445 hasConceptScore W166795445C2986087404 @default.
- W166795445 hasConceptScore W166795445C33923547 @default.
- W166795445 hasConceptScore W166795445C3454156 @default.
- W166795445 hasConceptScore W166795445C41008148 @default.
- W166795445 hasConceptScore W166795445C50817715 @default.
- W166795445 hasConceptScore W166795445C98763669 @default.
- W166795445 hasLocation W1667954451 @default.
- W166795445 hasOpenAccess W166795445 @default.
- W166795445 hasPrimaryLocation W1667954451 @default.
- W166795445 hasRelatedWork W1849095486 @default.
- W166795445 hasRelatedWork W2074680702 @default.
- W166795445 hasRelatedWork W2156211713 @default.
- W166795445 hasRelatedWork W2225522132 @default.
- W166795445 hasRelatedWork W2512014291 @default.
- W166795445 hasRelatedWork W2832404192 @default.
- W166795445 hasRelatedWork W2914115734 @default.
- W166795445 hasRelatedWork W2946284958 @default.
- W166795445 hasRelatedWork W2950133463 @default.
- W166795445 hasRelatedWork W2964118044 @default.
- W166795445 hasRelatedWork W2972710806 @default.
- W166795445 hasRelatedWork W2985982678 @default.
- W166795445 hasRelatedWork W3017390413 @default.
- W166795445 hasRelatedWork W3034327349 @default.
- W166795445 hasRelatedWork W3036081633 @default.
- W166795445 hasRelatedWork W3039913305 @default.
- W166795445 hasRelatedWork W3043157422 @default.
- W166795445 hasRelatedWork W3173628078 @default.
- W166795445 hasRelatedWork W3174075864 @default.
- W166795445 hasRelatedWork W3186835949 @default.
- W166795445 isParatext "false" @default.
- W166795445 isRetracted "false" @default.
- W166795445 magId "166795445" @default.
- W166795445 workType "article" @default.