Matches in SemOpenAlex for { <https://semopenalex.org/work/W2927014686> ?p ?o ?g. }
- W2927014686 abstract "End-to-end deep reinforcement learning has enabled agents to learn with little preprocessing by humans. However, it is still difficult to learn stably and efficiently because the learning method usually uses a nonlinear function approximation. Neural Episodic Control (NEC), which has been proposed in order to improve sample efficiency, is able to learn stably by estimating action values using a non-parametric method. In this paper, we propose an architecture that incorporates random projection into NEC to train with more stability. In addition, we verify the effectiveness of our architecture by Atari's five games. The main idea is to reduce the number of parameters that have to learn by replacing neural networks with random projection in order to reduce dimensions while keeping the learning end-to-end." @default.
- W2927014686 created "2019-04-11" @default.
- W2927014686 creator A5003753318 @default.
- W2927014686 creator A5046223937 @default.
- W2927014686 date "2019-04-03" @default.
- W2927014686 modified "2023-09-27" @default.
- W2927014686 title "Random Projection in Neural Episodic Control" @default.
- W2927014686 cites W1557517019 @default.
- W2927014686 cites W1572815477 @default.
- W2927014686 cites W1959608418 @default.
- W2927014686 cites W2041836310 @default.
- W2927014686 cites W2053171205 @default.
- W2927014686 cites W2056653303 @default.
- W2927014686 cites W2089497633 @default.
- W2927014686 cites W2134342155 @default.
- W2927014686 cites W2141559645 @default.
- W2927014686 cites W2145339207 @default.
- W2927014686 cites W2157988812 @default.
- W2927014686 cites W2165558283 @default.
- W2927014686 cites W2436711315 @default.
- W2927014686 cites W2593864460 @default.
- W2927014686 cites W2594466397 @default.
- W2927014686 cites W2610686804 @default.
- W2927014686 cites W2761873684 @default.
- W2927014686 cites W2890148520 @default.
- W2927014686 cites W2891076394 @default.
- W2927014686 cites W2902257694 @default.
- W2927014686 cites W2905801789 @default.
- W2927014686 cites W2915990637 @default.
- W2927014686 cites W2949951751 @default.
- W2927014686 cites W2952412806 @default.
- W2927014686 cites W2962831590 @default.
- W2927014686 cites W2963211300 @default.
- W2927014686 cites W2963477884 @default.
- W2927014686 cites W2964082094 @default.
- W2927014686 cites W2979473749 @default.
- W2927014686 hasPublicationYear "2019" @default.
- W2927014686 type Work @default.
- W2927014686 sameAs 2927014686 @default.
- W2927014686 citedByCount "0" @default.
- W2927014686 crossrefType "posted-content" @default.
- W2927014686 hasAuthorship W2927014686A5003753318 @default.
- W2927014686 hasAuthorship W2927014686A5046223937 @default.
- W2927014686 hasConcept C105795698 @default.
- W2927014686 hasConcept C112972136 @default.
- W2927014686 hasConcept C11413529 @default.
- W2927014686 hasConcept C117251300 @default.
- W2927014686 hasConcept C119857082 @default.
- W2927014686 hasConcept C121332964 @default.
- W2927014686 hasConcept C154945302 @default.
- W2927014686 hasConcept C155032097 @default.
- W2927014686 hasConcept C158622935 @default.
- W2927014686 hasConcept C2777036070 @default.
- W2927014686 hasConcept C2780791683 @default.
- W2927014686 hasConcept C33923547 @default.
- W2927014686 hasConcept C34736171 @default.
- W2927014686 hasConcept C41008148 @default.
- W2927014686 hasConcept C50644808 @default.
- W2927014686 hasConcept C57493831 @default.
- W2927014686 hasConcept C62520636 @default.
- W2927014686 hasConcept C97541855 @default.
- W2927014686 hasConceptScore W2927014686C105795698 @default.
- W2927014686 hasConceptScore W2927014686C112972136 @default.
- W2927014686 hasConceptScore W2927014686C11413529 @default.
- W2927014686 hasConceptScore W2927014686C117251300 @default.
- W2927014686 hasConceptScore W2927014686C119857082 @default.
- W2927014686 hasConceptScore W2927014686C121332964 @default.
- W2927014686 hasConceptScore W2927014686C154945302 @default.
- W2927014686 hasConceptScore W2927014686C155032097 @default.
- W2927014686 hasConceptScore W2927014686C158622935 @default.
- W2927014686 hasConceptScore W2927014686C2777036070 @default.
- W2927014686 hasConceptScore W2927014686C2780791683 @default.
- W2927014686 hasConceptScore W2927014686C33923547 @default.
- W2927014686 hasConceptScore W2927014686C34736171 @default.
- W2927014686 hasConceptScore W2927014686C41008148 @default.
- W2927014686 hasConceptScore W2927014686C50644808 @default.
- W2927014686 hasConceptScore W2927014686C57493831 @default.
- W2927014686 hasConceptScore W2927014686C62520636 @default.
- W2927014686 hasConceptScore W2927014686C97541855 @default.
- W2927014686 hasLocation W29270146861 @default.
- W2927014686 hasOpenAccess W2927014686 @default.
- W2927014686 hasPrimaryLocation W29270146861 @default.
- W2927014686 hasRelatedWork W1621787170 @default.
- W2927014686 hasRelatedWork W1931792391 @default.
- W2927014686 hasRelatedWork W2030040561 @default.
- W2927014686 hasRelatedWork W2147368400 @default.
- W2927014686 hasRelatedWork W2171277043 @default.
- W2927014686 hasRelatedWork W2204252256 @default.
- W2927014686 hasRelatedWork W2291973609 @default.
- W2927014686 hasRelatedWork W2619531655 @default.
- W2927014686 hasRelatedWork W2884778159 @default.
- W2927014686 hasRelatedWork W2920039561 @default.
- W2927014686 hasRelatedWork W2952569483 @default.
- W2927014686 hasRelatedWork W2962699241 @default.
- W2927014686 hasRelatedWork W3002177189 @default.
- W2927014686 hasRelatedWork W3035486480 @default.
- W2927014686 hasRelatedWork W3126611227 @default.
- W2927014686 hasRelatedWork W3132798516 @default.
- W2927014686 hasRelatedWork W3170588109 @default.
- W2927014686 hasRelatedWork W3170909290 @default.