Matches in SemOpenAlex for { <https://semopenalex.org/work/W2214971211> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2214971211 endingPage "2630" @default.
- W2214971211 startingPage "2624" @default.
- W2214971211 abstract "In many real-world situations a decision maker may make decisions across many separate reinforcement learning tasks in parallel, yet there has been very little work on concurrent RL. Building on the efficient exploration RL literature, we introduce two new concurrent RL algorithms and bound their sample complexity. We show that under some mild conditions, both when the agent is known to be acting in many copies of the same MDP, and when they are not the same but are taken from a finite set, we can gain linear improvements in the sample complexity over not sharing information. This is quite exciting as a linear speedup is the most one might hope to gain. Our preliminary experiments confirm this result and show empirical benefits." @default.
- W2214971211 created "2016-06-24" @default.
- W2214971211 creator A5084989076 @default.
- W2214971211 creator A5089902230 @default.
- W2214971211 date "2015-01-25" @default.
- W2214971211 modified "2023-09-26" @default.
- W2214971211 title "Concurrent PAC RL" @default.
- W2214971211 cites W107583932 @default.
- W2214971211 cites W1505937442 @default.
- W2214971211 cites W1517383877 @default.
- W2214971211 cites W1850488217 @default.
- W2214971211 cites W1988526405 @default.
- W2214971211 cites W2097381042 @default.
- W2214971211 cites W2099179721 @default.
- W2214971211 cites W2131479143 @default.
- W2214971211 cites W2142502798 @default.
- W2214971211 cites W2142620093 @default.
- W2214971211 cites W2143104527 @default.
- W2214971211 cites W2159517094 @default.
- W2214971211 cites W2159810454 @default.
- W2214971211 cites W2489939061 @default.
- W2214971211 cites W2964117027 @default.
- W2214971211 hasPublicationYear "2015" @default.
- W2214971211 type Work @default.
- W2214971211 sameAs 2214971211 @default.
- W2214971211 citedByCount "17" @default.
- W2214971211 countsByYear W22149712112015 @default.
- W2214971211 countsByYear W22149712112016 @default.
- W2214971211 countsByYear W22149712112018 @default.
- W2214971211 countsByYear W22149712112019 @default.
- W2214971211 countsByYear W22149712112020 @default.
- W2214971211 countsByYear W22149712112021 @default.
- W2214971211 crossrefType "proceedings-article" @default.
- W2214971211 hasAuthorship W2214971211A5084989076 @default.
- W2214971211 hasAuthorship W2214971211A5089902230 @default.
- W2214971211 hasConcept C120314980 @default.
- W2214971211 hasConcept C154945302 @default.
- W2214971211 hasConcept C173608175 @default.
- W2214971211 hasConcept C177264268 @default.
- W2214971211 hasConcept C185592680 @default.
- W2214971211 hasConcept C198531522 @default.
- W2214971211 hasConcept C199360897 @default.
- W2214971211 hasConcept C2778445095 @default.
- W2214971211 hasConcept C41008148 @default.
- W2214971211 hasConcept C43617362 @default.
- W2214971211 hasConcept C68339613 @default.
- W2214971211 hasConcept C80444323 @default.
- W2214971211 hasConcept C97541855 @default.
- W2214971211 hasConceptScore W2214971211C120314980 @default.
- W2214971211 hasConceptScore W2214971211C154945302 @default.
- W2214971211 hasConceptScore W2214971211C173608175 @default.
- W2214971211 hasConceptScore W2214971211C177264268 @default.
- W2214971211 hasConceptScore W2214971211C185592680 @default.
- W2214971211 hasConceptScore W2214971211C198531522 @default.
- W2214971211 hasConceptScore W2214971211C199360897 @default.
- W2214971211 hasConceptScore W2214971211C2778445095 @default.
- W2214971211 hasConceptScore W2214971211C41008148 @default.
- W2214971211 hasConceptScore W2214971211C43617362 @default.
- W2214971211 hasConceptScore W2214971211C68339613 @default.
- W2214971211 hasConceptScore W2214971211C80444323 @default.
- W2214971211 hasConceptScore W2214971211C97541855 @default.
- W2214971211 hasLocation W22149712111 @default.
- W2214971211 hasOpenAccess W2214971211 @default.
- W2214971211 hasPrimaryLocation W22149712111 @default.
- W2214971211 hasRelatedWork W1658008008 @default.
- W2214971211 hasRelatedWork W1771410628 @default.
- W2214971211 hasRelatedWork W1850488217 @default.
- W2214971211 hasRelatedWork W2121863487 @default.
- W2214971211 hasRelatedWork W2142620093 @default.
- W2214971211 hasRelatedWork W21891419 @default.
- W2214971211 hasRelatedWork W2289410116 @default.
- W2214971211 hasRelatedWork W2489939061 @default.
- W2214971211 hasRelatedWork W2528846071 @default.
- W2214971211 hasRelatedWork W2567415945 @default.
- W2214971211 hasRelatedWork W2736601468 @default.
- W2214971211 hasRelatedWork W2936107880 @default.
- W2214971211 hasRelatedWork W2962910611 @default.
- W2214971211 hasRelatedWork W2970650844 @default.
- W2214971211 hasRelatedWork W2988077171 @default.
- W2214971211 hasRelatedWork W3037924899 @default.
- W2214971211 hasRelatedWork W3038032959 @default.
- W2214971211 hasRelatedWork W3165994454 @default.
- W2214971211 hasRelatedWork W3169514089 @default.
- W2214971211 hasRelatedWork W3170914142 @default.
- W2214971211 isParatext "false" @default.
- W2214971211 isRetracted "false" @default.
- W2214971211 magId "2214971211" @default.
- W2214971211 workType "article" @default.