Matches in SemOpenAlex for { <https://semopenalex.org/work/W2117941808> ?p ?o ?g. }
- W2117941808 endingPage "1220" @default.
- W2117941808 startingPage "1207" @default.
- W2117941808 abstract "The key approaches for machine learning, particularly learning in unknown probabilistic environments, are new representations and computation mechanisms. In this paper, a novel quantum reinforcement learning (QRL) method is proposed by combining quantum theory and reinforcement learning (RL). Inspired by the state superposition principle and quantum parallelism, a framework of a value-updating algorithm is introduced. The state (action) in traditional RL is identified as the eigen state (eigen action) in QRL. The state (action) set can be represented with a quantum superposition state, and the eigen state (eigen action) can be obtained by randomly observing the simulated quantum state according to the collapse postulate of quantum measurement. The probability of the eigen action is determined by the probability amplitude, which is updated in parallel according to rewards. Some related characteristics of QRL such as convergence, optimality, and balancing between exploration and exploitation are also analyzed, which shows that this approach makes a good tradeoff between exploration and exploitation using the probability amplitude and can speedup learning through the quantum parallelism. To evaluate the performance and practicability of QRL, several simulated experiments are given, and the results demonstrate the effectiveness and superiority of the QRL algorithm for some complex problems. This paper is also an effective exploration on the application of quantum computation to artificial intelligence." @default.
- W2117941808 created "2016-06-24" @default.
- W2117941808 creator A5000582423 @default.
- W2117941808 creator A5030229878 @default.
- W2117941808 creator A5051368351 @default.
- W2117941808 creator A5054800972 @default.
- W2117941808 date "2008-10-01" @default.
- W2117941808 modified "2023-10-10" @default.
- W2117941808 title "Quantum Reinforcement Learning" @default.
- W2117941808 cites W1551593752 @default.
- W2117941808 cites W1585003050 @default.
- W2117941808 cites W1592847719 @default.
- W2117941808 cites W1970468954 @default.
- W2117941808 cites W1970498158 @default.
- W2117941808 cites W1979260239 @default.
- W2117941808 cites W1980910057 @default.
- W2117941808 cites W1992574024 @default.
- W2117941808 cites W1996519437 @default.
- W2117941808 cites W2002372750 @default.
- W2117941808 cites W2006202580 @default.
- W2117941808 cites W2032675708 @default.
- W2117941808 cites W2043353432 @default.
- W2117941808 cites W2045463255 @default.
- W2117941808 cites W2055784634 @default.
- W2117941808 cites W2056325504 @default.
- W2117941808 cites W2063467433 @default.
- W2117941808 cites W2084652510 @default.
- W2117941808 cites W2103278447 @default.
- W2117941808 cites W2103285838 @default.
- W2117941808 cites W2106155860 @default.
- W2117941808 cites W2107726111 @default.
- W2117941808 cites W2109910161 @default.
- W2117941808 cites W2116422303 @default.
- W2117941808 cites W2121517924 @default.
- W2117941808 cites W2126185879 @default.
- W2117941808 cites W2126357802 @default.
- W2117941808 cites W2128024939 @default.
- W2117941808 cites W2130751725 @default.
- W2117941808 cites W2142196876 @default.
- W2117941808 cites W2150999967 @default.
- W2117941808 cites W2154727892 @default.
- W2117941808 cites W2159226773 @default.
- W2117941808 cites W2161802186 @default.
- W2117941808 cites W2168676717 @default.
- W2117941808 cites W2582029817 @default.
- W2117941808 cites W2912185451 @default.
- W2117941808 cites W2913329048 @default.
- W2117941808 cites W3041202696 @default.
- W2117941808 cites W3101558632 @default.
- W2117941808 cites W3101834087 @default.
- W2117941808 cites W3106123690 @default.
- W2117941808 cites W32403112 @default.
- W2117941808 doi "https://doi.org/10.1109/tsmcb.2008.925743" @default.
- W2117941808 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/18784007" @default.
- W2117941808 hasPublicationYear "2008" @default.
- W2117941808 type Work @default.
- W2117941808 sameAs 2117941808 @default.
- W2117941808 citedByCount "237" @default.
- W2117941808 countsByYear W21179418082012 @default.
- W2117941808 countsByYear W21179418082013 @default.
- W2117941808 countsByYear W21179418082014 @default.
- W2117941808 countsByYear W21179418082015 @default.
- W2117941808 countsByYear W21179418082016 @default.
- W2117941808 countsByYear W21179418082017 @default.
- W2117941808 countsByYear W21179418082018 @default.
- W2117941808 countsByYear W21179418082019 @default.
- W2117941808 countsByYear W21179418082020 @default.
- W2117941808 countsByYear W21179418082021 @default.
- W2117941808 countsByYear W21179418082022 @default.
- W2117941808 countsByYear W21179418082023 @default.
- W2117941808 crossrefType "journal-article" @default.
- W2117941808 hasAuthorship W2117941808A5000582423 @default.
- W2117941808 hasAuthorship W2117941808A5030229878 @default.
- W2117941808 hasAuthorship W2117941808A5051368351 @default.
- W2117941808 hasAuthorship W2117941808A5054800972 @default.
- W2117941808 hasConcept C11255438 @default.
- W2117941808 hasConcept C11413529 @default.
- W2117941808 hasConcept C121332964 @default.
- W2117941808 hasConcept C126255220 @default.
- W2117941808 hasConcept C134306372 @default.
- W2117941808 hasConcept C137019171 @default.
- W2117941808 hasConcept C15184713 @default.
- W2117941808 hasConcept C154945302 @default.
- W2117941808 hasConcept C15706264 @default.
- W2117941808 hasConcept C173608175 @default.
- W2117941808 hasConcept C188116033 @default.
- W2117941808 hasConcept C27753989 @default.
- W2117941808 hasConcept C33923547 @default.
- W2117941808 hasConcept C41008148 @default.
- W2117941808 hasConcept C45374587 @default.
- W2117941808 hasConcept C49937458 @default.
- W2117941808 hasConcept C55615164 @default.
- W2117941808 hasConcept C58053490 @default.
- W2117941808 hasConcept C62520636 @default.
- W2117941808 hasConcept C68339613 @default.
- W2117941808 hasConcept C80444323 @default.
- W2117941808 hasConcept C84114770 @default.
- W2117941808 hasConcept C94231801 @default.