Matches in SemOpenAlex for { <https://semopenalex.org/work/W2904148778> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W2904148778 abstract "Efficient Reinforcement Learning usually takes advantage of demonstration or good exploration strategy. By applying posterior sampling in model-free RL under the hypothesis of GP, we propose Gaussian Process Posterior Sampling Reinforcement Learning(GPPSTD) algorithm in continuous state space, giving theoretical justifications and empirical results. We also provide theoretical and empirical results that various demonstration could lower expected uncertainty and benefit posterior sampling exploration. In this way, we combined the demonstration and exploration process together to achieve a more efficient reinforcement learning." @default.
- W2904148778 created "2018-12-22" @default.
- W2904148778 creator A5001498982 @default.
- W2904148778 creator A5049891156 @default.
- W2904148778 creator A5076130143 @default.
- W2904148778 date "2018-12-11" @default.
- W2904148778 modified "2023-10-18" @default.
- W2904148778 title "Efficient Model-Free Reinforcement Learning Using Gaussian Process" @default.
- W2904148778 cites W1591675293 @default.
- W2904148778 cites W1848006316 @default.
- W2904148778 cites W1945133117 @default.
- W2904148778 cites W1984615387 @default.
- W2904148778 cites W1999874108 @default.
- W2904148778 cites W2061562262 @default.
- W2904148778 cites W2098774185 @default.
- W2904148778 cites W2132849848 @default.
- W2904148778 cites W2142620093 @default.
- W2904148778 cites W2145339207 @default.
- W2904148778 cites W2156974606 @default.
- W2904148778 cites W2257979135 @default.
- W2904148778 cites W2434014514 @default.
- W2904148778 cites W2614839826 @default.
- W2904148778 cites W2621205314 @default.
- W2904148778 cites W2724169821 @default.
- W2904148778 cites W2731829640 @default.
- W2904148778 cites W2788862220 @default.
- W2904148778 cites W2962957031 @default.
- W2904148778 cites W2963158178 @default.
- W2904148778 doi "https://doi.org/10.48550/arxiv.1812.04359" @default.
- W2904148778 hasPublicationYear "2018" @default.
- W2904148778 type Work @default.
- W2904148778 sameAs 2904148778 @default.
- W2904148778 citedByCount "1" @default.
- W2904148778 countsByYear W29041487782020 @default.
- W2904148778 crossrefType "posted-content" @default.
- W2904148778 hasAuthorship W2904148778A5001498982 @default.
- W2904148778 hasAuthorship W2904148778A5049891156 @default.
- W2904148778 hasAuthorship W2904148778A5076130143 @default.
- W2904148778 hasBestOaLocation W29041487781 @default.
- W2904148778 hasConcept C105795698 @default.
- W2904148778 hasConcept C106131492 @default.
- W2904148778 hasConcept C107673813 @default.
- W2904148778 hasConcept C111919701 @default.
- W2904148778 hasConcept C119857082 @default.
- W2904148778 hasConcept C121332964 @default.
- W2904148778 hasConcept C127413603 @default.
- W2904148778 hasConcept C140779682 @default.
- W2904148778 hasConcept C154945302 @default.
- W2904148778 hasConcept C163716315 @default.
- W2904148778 hasConcept C2778572836 @default.
- W2904148778 hasConcept C31972630 @default.
- W2904148778 hasConcept C33923547 @default.
- W2904148778 hasConcept C41008148 @default.
- W2904148778 hasConcept C57830394 @default.
- W2904148778 hasConcept C61326573 @default.
- W2904148778 hasConcept C62520636 @default.
- W2904148778 hasConcept C66938386 @default.
- W2904148778 hasConcept C67203356 @default.
- W2904148778 hasConcept C72434380 @default.
- W2904148778 hasConcept C97541855 @default.
- W2904148778 hasConcept C98045186 @default.
- W2904148778 hasConceptScore W2904148778C105795698 @default.
- W2904148778 hasConceptScore W2904148778C106131492 @default.
- W2904148778 hasConceptScore W2904148778C107673813 @default.
- W2904148778 hasConceptScore W2904148778C111919701 @default.
- W2904148778 hasConceptScore W2904148778C119857082 @default.
- W2904148778 hasConceptScore W2904148778C121332964 @default.
- W2904148778 hasConceptScore W2904148778C127413603 @default.
- W2904148778 hasConceptScore W2904148778C140779682 @default.
- W2904148778 hasConceptScore W2904148778C154945302 @default.
- W2904148778 hasConceptScore W2904148778C163716315 @default.
- W2904148778 hasConceptScore W2904148778C2778572836 @default.
- W2904148778 hasConceptScore W2904148778C31972630 @default.
- W2904148778 hasConceptScore W2904148778C33923547 @default.
- W2904148778 hasConceptScore W2904148778C41008148 @default.
- W2904148778 hasConceptScore W2904148778C57830394 @default.
- W2904148778 hasConceptScore W2904148778C61326573 @default.
- W2904148778 hasConceptScore W2904148778C62520636 @default.
- W2904148778 hasConceptScore W2904148778C66938386 @default.
- W2904148778 hasConceptScore W2904148778C67203356 @default.
- W2904148778 hasConceptScore W2904148778C72434380 @default.
- W2904148778 hasConceptScore W2904148778C97541855 @default.
- W2904148778 hasConceptScore W2904148778C98045186 @default.
- W2904148778 hasLocation W29041487781 @default.
- W2904148778 hasOpenAccess W2904148778 @default.
- W2904148778 hasPrimaryLocation W29041487781 @default.
- W2904148778 hasRelatedWork W1564932097 @default.
- W2904148778 hasRelatedWork W2017957758 @default.
- W2904148778 hasRelatedWork W2251221343 @default.
- W2904148778 hasRelatedWork W2357135621 @default.
- W2904148778 hasRelatedWork W2904148778 @default.
- W2904148778 hasRelatedWork W3009457412 @default.
- W2904148778 hasRelatedWork W3022038857 @default.
- W2904148778 hasRelatedWork W3123425514 @default.
- W2904148778 hasRelatedWork W3170446423 @default.
- W2904148778 hasRelatedWork W4319083788 @default.
- W2904148778 isParatext "false" @default.
- W2904148778 isRetracted "false" @default.
- W2904148778 magId "2904148778" @default.
- W2904148778 workType "article" @default.