Matches in SemOpenAlex for { <https://semopenalex.org/work/W2940734525> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2940734525 abstract "Deep reinforcement learning (DRL) has achieved significant breakthroughs in various tasks. However, most DRL algorithms suffer a problem of generalizing the learned policy which makes the learning performance largely affected even by minor modifications of the training environment. Except that, the use of deep neural networks makes the learned policies hard to be interpretable. To address these two challenges, we propose a novel algorithm named Neural Logic Reinforcement Learning (NLRL) to represent the policies in reinforcement learning by first-order logic. NLRL is based on policy gradient methods and differentiable inductive logic programming that have demonstrated significant advantages in terms of interpretability and generalisability in supervised tasks. Extensive experiments conducted on cliff-walking and blocks manipulation tasks demonstrate that NLRL can induce interpretable policies achieving near-optimal performance while demonstrating good generalisability to environments of different initial states and problem sizes." @default.
- W2940734525 created "2019-05-03" @default.
- W2940734525 creator A5012646628 @default.
- W2940734525 creator A5085148839 @default.
- W2940734525 date "2019-04-24" @default.
- W2940734525 modified "2023-09-27" @default.
- W2940734525 title "Neural Logic Reinforcement Learning" @default.
- W2940734525 cites W1191599655 @default.
- W2940734525 cites W1505515950 @default.
- W2940734525 cites W1515851193 @default.
- W2940734525 cites W1585529040 @default.
- W2940734525 cites W1654728867 @default.
- W2940734525 cites W1665214252 @default.
- W2940734525 cites W1771410628 @default.
- W2940734525 cites W1800916125 @default.
- W2940734525 cites W2095705004 @default.
- W2940734525 cites W2119717200 @default.
- W2940734525 cites W2133632477 @default.
- W2940734525 cites W2134153324 @default.
- W2940734525 cites W2145339207 @default.
- W2940734525 cites W2148411640 @default.
- W2940734525 cites W2594475271 @default.
- W2940734525 cites W2736601468 @default.
- W2940734525 cites W2738790068 @default.
- W2940734525 cites W2766447205 @default.
- W2940734525 cites W2785948534 @default.
- W2940734525 cites W2797527950 @default.
- W2940734525 cites W2949608212 @default.
- W2940734525 cites W2951124598 @default.
- W2940734525 cites W2962875487 @default.
- W2940734525 cites W2962924847 @default.
- W2940734525 cites W2964043796 @default.
- W2940734525 cites W2964310273 @default.
- W2940734525 cites W2967311966 @default.
- W2940734525 cites W3020831056 @default.
- W2940734525 cites W3021539726 @default.
- W2940734525 hasPublicationYear "2019" @default.
- W2940734525 type Work @default.
- W2940734525 sameAs 2940734525 @default.
- W2940734525 citedByCount "0" @default.
- W2940734525 crossrefType "posted-content" @default.
- W2940734525 hasAuthorship W2940734525A5012646628 @default.
- W2940734525 hasAuthorship W2940734525A5085148839 @default.
- W2940734525 hasConcept C119857082 @default.
- W2940734525 hasConcept C134306372 @default.
- W2940734525 hasConcept C154945302 @default.
- W2940734525 hasConcept C202615002 @default.
- W2940734525 hasConcept C2779382394 @default.
- W2940734525 hasConcept C2781067378 @default.
- W2940734525 hasConcept C2984842247 @default.
- W2940734525 hasConcept C33923547 @default.
- W2940734525 hasConcept C41008148 @default.
- W2940734525 hasConcept C50644808 @default.
- W2940734525 hasConcept C97541855 @default.
- W2940734525 hasConceptScore W2940734525C119857082 @default.
- W2940734525 hasConceptScore W2940734525C134306372 @default.
- W2940734525 hasConceptScore W2940734525C154945302 @default.
- W2940734525 hasConceptScore W2940734525C202615002 @default.
- W2940734525 hasConceptScore W2940734525C2779382394 @default.
- W2940734525 hasConceptScore W2940734525C2781067378 @default.
- W2940734525 hasConceptScore W2940734525C2984842247 @default.
- W2940734525 hasConceptScore W2940734525C33923547 @default.
- W2940734525 hasConceptScore W2940734525C41008148 @default.
- W2940734525 hasConceptScore W2940734525C50644808 @default.
- W2940734525 hasConceptScore W2940734525C97541855 @default.
- W2940734525 hasLocation W29407345251 @default.
- W2940734525 hasOpenAccess W2940734525 @default.
- W2940734525 hasPrimaryLocation W29407345251 @default.
- W2940734525 hasRelatedWork W2521274174 @default.
- W2940734525 hasRelatedWork W2606433045 @default.
- W2940734525 hasRelatedWork W2623259071 @default.
- W2940734525 hasRelatedWork W2735995851 @default.
- W2940734525 hasRelatedWork W2892858663 @default.
- W2940734525 hasRelatedWork W2946824041 @default.
- W2940734525 hasRelatedWork W2963557365 @default.
- W2940734525 hasRelatedWork W2964464273 @default.
- W2940734525 hasRelatedWork W2971919016 @default.
- W2940734525 hasRelatedWork W3010862467 @default.
- W2940734525 hasRelatedWork W3035521307 @default.
- W2940734525 hasRelatedWork W3084024636 @default.
- W2940734525 hasRelatedWork W3091395917 @default.
- W2940734525 hasRelatedWork W3109409708 @default.
- W2940734525 hasRelatedWork W3118515108 @default.
- W2940734525 hasRelatedWork W3131310681 @default.
- W2940734525 hasRelatedWork W3201666735 @default.
- W2940734525 hasRelatedWork W3206895853 @default.
- W2940734525 hasRelatedWork W3208540476 @default.
- W2940734525 hasRelatedWork W91463945 @default.
- W2940734525 isParatext "false" @default.
- W2940734525 isRetracted "false" @default.
- W2940734525 magId "2940734525" @default.
- W2940734525 workType "article" @default.