Matches in SemOpenAlex for { <https://semopenalex.org/work/W2159178228> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2159178228 abstract "Model-based Bayesian Reinforcement Learning (BRL) allows a found formalization of the problem of acting optimally while facing an unknown environment, i.e., avoiding the exploration-exploitation dilemma. However, algorithms explicitly addressing BRL suffer from such a combinatorial explosion that a large body of work relies on heuristic algorithms. This paper introduces BOLT, a simple and (almost) deterministic heuristic algorithm for BRL which is optimistic about the transition function. We analyze BOLT's sample complexity, and show that under certain parameters, the algorithm is near-optimal in the Bayesian sense with high probability. Then, experimental results highlight the key differences of this method compared to previous work." @default.
- W2159178228 created "2016-06-24" @default.
- W2159178228 creator A5022343068 @default.
- W2159178228 creator A5037765124 @default.
- W2159178228 creator A5079283943 @default.
- W2159178228 date "2012-06-26" @default.
- W2159178228 modified "2023-09-26" @default.
- W2159178228 title "Near-Optimal BRL using Optimistic Local Transitions" @default.
- W2159178228 cites W1008992527 @default.
- W2159178228 cites W1497039698 @default.
- W2159178228 cites W1505937442 @default.
- W2159178228 cites W1515851193 @default.
- W2159178228 cites W1526654727 @default.
- W2159178228 cites W1582436621 @default.
- W2159178228 cites W2019363670 @default.
- W2159178228 cites W2116459397 @default.
- W2159178228 cites W2119567691 @default.
- W2159178228 cites W2121863487 @default.
- W2159178228 cites W2123447947 @default.
- W2159178228 cites W2124352385 @default.
- W2159178228 cites W2125710232 @default.
- W2159178228 cites W2127186087 @default.
- W2159178228 cites W2489939061 @default.
- W2159178228 cites W2963214119 @default.
- W2159178228 cites W3023407077 @default.
- W2159178228 hasPublicationYear "2012" @default.
- W2159178228 type Work @default.
- W2159178228 sameAs 2159178228 @default.
- W2159178228 citedByCount "17" @default.
- W2159178228 countsByYear W21591782282013 @default.
- W2159178228 countsByYear W21591782282014 @default.
- W2159178228 countsByYear W21591782282015 @default.
- W2159178228 countsByYear W21591782282018 @default.
- W2159178228 crossrefType "proceedings-article" @default.
- W2159178228 hasAuthorship W2159178228A5022343068 @default.
- W2159178228 hasAuthorship W2159178228A5037765124 @default.
- W2159178228 hasAuthorship W2159178228A5079283943 @default.
- W2159178228 hasBestOaLocation W21591782281 @default.
- W2159178228 hasConcept C107673813 @default.
- W2159178228 hasConcept C111472728 @default.
- W2159178228 hasConcept C11413529 @default.
- W2159178228 hasConcept C126255220 @default.
- W2159178228 hasConcept C138885662 @default.
- W2159178228 hasConcept C14036430 @default.
- W2159178228 hasConcept C154945302 @default.
- W2159178228 hasConcept C173801870 @default.
- W2159178228 hasConcept C26517878 @default.
- W2159178228 hasConcept C2778445095 @default.
- W2159178228 hasConcept C2780586882 @default.
- W2159178228 hasConcept C33923547 @default.
- W2159178228 hasConcept C38652104 @default.
- W2159178228 hasConcept C41008148 @default.
- W2159178228 hasConcept C78458016 @default.
- W2159178228 hasConcept C86803240 @default.
- W2159178228 hasConcept C97541855 @default.
- W2159178228 hasConceptScore W2159178228C107673813 @default.
- W2159178228 hasConceptScore W2159178228C111472728 @default.
- W2159178228 hasConceptScore W2159178228C11413529 @default.
- W2159178228 hasConceptScore W2159178228C126255220 @default.
- W2159178228 hasConceptScore W2159178228C138885662 @default.
- W2159178228 hasConceptScore W2159178228C14036430 @default.
- W2159178228 hasConceptScore W2159178228C154945302 @default.
- W2159178228 hasConceptScore W2159178228C173801870 @default.
- W2159178228 hasConceptScore W2159178228C26517878 @default.
- W2159178228 hasConceptScore W2159178228C2778445095 @default.
- W2159178228 hasConceptScore W2159178228C2780586882 @default.
- W2159178228 hasConceptScore W2159178228C33923547 @default.
- W2159178228 hasConceptScore W2159178228C38652104 @default.
- W2159178228 hasConceptScore W2159178228C41008148 @default.
- W2159178228 hasConceptScore W2159178228C78458016 @default.
- W2159178228 hasConceptScore W2159178228C86803240 @default.
- W2159178228 hasConceptScore W2159178228C97541855 @default.
- W2159178228 hasLocation W21591782281 @default.
- W2159178228 hasLocation W21591782282 @default.
- W2159178228 hasLocation W21591782283 @default.
- W2159178228 hasLocation W21591782284 @default.
- W2159178228 hasOpenAccess W2159178228 @default.
- W2159178228 hasPrimaryLocation W21591782281 @default.
- W2159178228 hasRelatedWork W1915057100 @default.
- W2159178228 hasRelatedWork W260766989 @default.
- W2159178228 hasRelatedWork W2800834205 @default.
- W2159178228 hasRelatedWork W2959276766 @default.
- W2159178228 hasRelatedWork W3074294383 @default.
- W2159178228 hasRelatedWork W3111983280 @default.
- W2159178228 hasRelatedWork W3139193008 @default.
- W2159178228 hasRelatedWork W3214955173 @default.
- W2159178228 hasRelatedWork W4206669594 @default.
- W2159178228 hasRelatedWork W4295941380 @default.
- W2159178228 isParatext "false" @default.
- W2159178228 isRetracted "false" @default.
- W2159178228 magId "2159178228" @default.
- W2159178228 workType "article" @default.