Matches in SemOpenAlex for { <https://semopenalex.org/work/W2200297111> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W2200297111 abstract "We consider how to learn multi-step predictions efficiently. Conventional algorithms wait until observing actual outcomes before performing the computations to update their predictions. If predictions are made at a high rate or span over a large amount of time, substantial computation can be required to store all relevant observations and to update all predictions when the outcome is finally observed. We show that the exact same predictions can be learned in a much more computationally congenial way, with uniform per-step computation that does not depend on the span of the predictions. We apply this idea to various settings of increasing generality, repeatedly adding desired properties and each time deriving an equivalent span-independent algorithm for the conventional algorithm that satisfies these desiderata. Interestingly, along the way several known algorithmic constructs emerge spontaneously from our derivations, including dutch eligibility traces, temporal difference errors, and averaging. This allows us to link these constructs one-to-one to the corresponding desiderata, unambiguously connecting the `how' to the `why'. Each step, we make sure that the derived algorithm subsumes the previous algorithms, thereby retaining their properties. Ultimately we arrive at a single general temporal-difference algorithm that is applicable to the full setting of reinforcement learning." @default.
- W2200297111 created "2016-06-24" @default.
- W2200297111 creator A5004923102 @default.
- W2200297111 creator A5033135596 @default.
- W2200297111 date "2015-08-19" @default.
- W2200297111 modified "2023-09-27" @default.
- W2200297111 title "Learning to Predict Independent of Span" @default.
- W2200297111 cites W1499021337 @default.
- W2200297111 cites W1569296262 @default.
- W2200297111 cites W1985291828 @default.
- W2200297111 cites W1994616650 @default.
- W2200297111 cites W2028145673 @default.
- W2200297111 cites W2072931156 @default.
- W2200297111 cites W2073384958 @default.
- W2200297111 cites W2075268401 @default.
- W2200297111 cites W2086161653 @default.
- W2200297111 cites W2094364653 @default.
- W2200297111 cites W2100677568 @default.
- W2200297111 cites W2107741520 @default.
- W2200297111 cites W2115286699 @default.
- W2200297111 cites W2121863487 @default.
- W2200297111 cites W2145339207 @default.
- W2200297111 cites W2159930037 @default.
- W2200297111 cites W2188892596 @default.
- W2200297111 cites W2341171179 @default.
- W2200297111 cites W2798579099 @default.
- W2200297111 cites W2919115771 @default.
- W2200297111 cites W75509695 @default.
- W2200297111 hasPublicationYear "2015" @default.
- W2200297111 type Work @default.
- W2200297111 sameAs 2200297111 @default.
- W2200297111 citedByCount "11" @default.
- W2200297111 countsByYear W22002971112015 @default.
- W2200297111 countsByYear W22002971112016 @default.
- W2200297111 countsByYear W22002971112018 @default.
- W2200297111 countsByYear W22002971112019 @default.
- W2200297111 countsByYear W22002971112020 @default.
- W2200297111 countsByYear W22002971112021 @default.
- W2200297111 crossrefType "posted-content" @default.
- W2200297111 hasAuthorship W2200297111A5004923102 @default.
- W2200297111 hasAuthorship W2200297111A5033135596 @default.
- W2200297111 hasConcept C11413529 @default.
- W2200297111 hasConcept C127413603 @default.
- W2200297111 hasConcept C147176958 @default.
- W2200297111 hasConcept C15744967 @default.
- W2200297111 hasConcept C2778753569 @default.
- W2200297111 hasConcept C2780767217 @default.
- W2200297111 hasConcept C41008148 @default.
- W2200297111 hasConcept C45374587 @default.
- W2200297111 hasConcept C542102704 @default.
- W2200297111 hasConceptScore W2200297111C11413529 @default.
- W2200297111 hasConceptScore W2200297111C127413603 @default.
- W2200297111 hasConceptScore W2200297111C147176958 @default.
- W2200297111 hasConceptScore W2200297111C15744967 @default.
- W2200297111 hasConceptScore W2200297111C2778753569 @default.
- W2200297111 hasConceptScore W2200297111C2780767217 @default.
- W2200297111 hasConceptScore W2200297111C41008148 @default.
- W2200297111 hasConceptScore W2200297111C45374587 @default.
- W2200297111 hasConceptScore W2200297111C542102704 @default.
- W2200297111 hasLocation W22002971111 @default.
- W2200297111 hasOpenAccess W2200297111 @default.
- W2200297111 hasPrimaryLocation W22002971111 @default.
- W2200297111 hasRelatedWork W1533114612 @default.
- W2200297111 hasRelatedWork W2075268401 @default.
- W2200297111 hasRelatedWork W2100677568 @default.
- W2200297111 hasRelatedWork W2121863487 @default.
- W2200297111 hasRelatedWork W2132622533 @default.
- W2200297111 hasRelatedWork W2141559645 @default.
- W2200297111 hasRelatedWork W2145339207 @default.
- W2200297111 hasRelatedWork W2159752377 @default.
- W2200297111 hasRelatedWork W2188892596 @default.
- W2200297111 hasRelatedWork W2531264864 @default.
- W2200297111 hasRelatedWork W2892521964 @default.
- W2200297111 hasRelatedWork W2970202659 @default.
- W2200297111 hasRelatedWork W3011120880 @default.
- W2200297111 hasRelatedWork W3098041469 @default.
- W2200297111 hasRelatedWork W3103780890 @default.
- W2200297111 hasRelatedWork W3168353947 @default.
- W2200297111 hasRelatedWork W3174732583 @default.
- W2200297111 hasRelatedWork W3213622222 @default.
- W2200297111 hasRelatedWork W2397860154 @default.
- W2200297111 hasRelatedWork W2736541554 @default.
- W2200297111 isParatext "false" @default.
- W2200297111 isRetracted "false" @default.
- W2200297111 magId "2200297111" @default.
- W2200297111 workType "article" @default.