<?xml version="1.0" encoding="ISO-8859-1"?><article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
<front>
<journal-meta>
<journal-id>1405-5546</journal-id>
<journal-title><![CDATA[Computación y Sistemas]]></journal-title>
<abbrev-journal-title><![CDATA[Comp. y Sist.]]></abbrev-journal-title>
<issn>1405-5546</issn>
<publisher>
<publisher-name><![CDATA[Instituto Politécnico Nacional, Centro de Investigación en Computación]]></publisher-name>
</publisher>
</journal-meta>
<article-meta>
<article-id>S1405-55462024000200353</article-id>
<article-id pub-id-type="doi">10.13053/cys-28-2-4723</article-id>
<title-group>
<article-title xml:lang="en"><![CDATA[Policy Gradient MaxSAT Solver]]></article-title>
</title-group>
<contrib-group>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Gutiérrez-De-La-Paz]]></surname>
<given-names><![CDATA[Omar]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Menchaca-Méndez]]></surname>
<given-names><![CDATA[Ricardo]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Zamora-Gómez]]></surname>
<given-names><![CDATA[Erik]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Corona-Bermúdez]]></surname>
<given-names><![CDATA[Uriel]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Menchaca-Méndez]]></surname>
<given-names><![CDATA[Rolando]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Gutiérrez-De-La-Paz]]></surname>
<given-names><![CDATA[Bruno]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
</contrib-group>
<aff id="Af1">
<institution><![CDATA[,Instituto Politécnico Nacional Centro de Investigación en Computación ]]></institution>
<addr-line><![CDATA[ ]]></addr-line>
<country>Mexico</country>
</aff>
<pub-date pub-type="pub">
<day>00</day>
<month>06</month>
<year>2024</year>
</pub-date>
<pub-date pub-type="epub">
<day>00</day>
<month>06</month>
<year>2024</year>
</pub-date>
<volume>28</volume>
<numero>2</numero>
<fpage>353</fpage>
<lpage>366</lpage>
<copyright-statement/>
<copyright-year/>
<self-uri xlink:href="http://www.scielo.org.mx/scielo.php?script=sci_arttext&amp;pid=S1405-55462024000200353&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.mx/scielo.php?script=sci_abstract&amp;pid=S1405-55462024000200353&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.mx/scielo.php?script=sci_pdf&amp;pid=S1405-55462024000200353&amp;lng=en&amp;nrm=iso"></self-uri><abstract abstract-type="short" xml:lang="en"><p><![CDATA[Abstract: This paper presents a comparative study of various elements and strategies that can be incorporated into an autoregressive model to address the MaxSAT problem. Building upon a sequential architecture as our foundation, we optimize the model&#8217;s parameters by maximizing the expected number of satisfied clauses. This optimization enables the model, given a SAT formula, to predict a distribution over potential solutions using the policy gradient method. Our controlled experiments pinpoint elements that guide the optimization process towards superior resultsfn.]]></p></abstract>
<kwd-group>
<kwd lng="en"><![CDATA[MaxSAT problem]]></kwd>
<kwd lng="en"><![CDATA[policy gradient]]></kwd>
<kwd lng="en"><![CDATA[NP-hard]]></kwd>
</kwd-group>
</article-meta>
</front><back>
<ref-list>
<ref id="B1">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Akiba]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
<name>
<surname><![CDATA[Sano]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Yanase]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
<name>
<surname><![CDATA[Ohta]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
<name>
<surname><![CDATA[Koyama]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
</person-group>
<source><![CDATA[Optuna: A next-generation hyperparameter optimization framework]]></source>
<year>2019</year>
<conf-name><![CDATA[ 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining]]></conf-name>
<conf-loc> </conf-loc>
<page-range>2623-31</page-range></nlm-citation>
</ref>
<ref id="B2">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Avellaneda]]></surname>
<given-names><![CDATA[F.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[A short description of the solver EvalMaxSAT]]></article-title>
<source><![CDATA[MaxSAT Evaluation]]></source>
<year>2020</year>
<volume>8</volume>
</nlm-citation>
</ref>
<ref id="B3">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Bacchus]]></surname>
<given-names><![CDATA[F.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[MaxHS in the 2022 MaxSAT evaluation]]></article-title>
<source><![CDATA[MaxSAT Evaluation 2022]]></source>
<year>2022</year>
<volume>B-2022</volume>
<page-range>17-8</page-range></nlm-citation>
</ref>
<ref id="B4">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Bello]]></surname>
<given-names><![CDATA[I.]]></given-names>
</name>
<name>
<surname><![CDATA[Pham]]></surname>
<given-names><![CDATA[H.]]></given-names>
</name>
<name>
<surname><![CDATA[Le]]></surname>
<given-names><![CDATA[Q. V.]]></given-names>
</name>
<name>
<surname><![CDATA[Norouzi]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Bengio]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
</person-group>
<source><![CDATA[Neural combinatorial optimization with reinforcement learning]]></source>
<year>2016</year>
<conf-name><![CDATA[ 5th International Conference on Learning Representations]]></conf-name>
<conf-loc> </conf-loc>
</nlm-citation>
</ref>
<ref id="B5">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Bengio]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
<name>
<surname><![CDATA[Lodi]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Prouvost]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Machine learning for combinatorial optimization: A methodological tour d&#8217;horizon]]></article-title>
<source><![CDATA[European Journal of Operational Research]]></source>
<year>2021</year>
<volume>290</volume>
<numero>2</numero>
<issue>2</issue>
<page-range>405-21</page-range></nlm-citation>
</ref>
<ref id="B6">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Berg]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Demirovi&#263;]]></surname>
<given-names><![CDATA[E.]]></given-names>
</name>
<name>
<surname><![CDATA[Stuckey]]></surname>
<given-names><![CDATA[P. J.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Core-boosted linear search for incomplete MaxSAT]]></article-title>
<person-group person-group-type="editor">
<name>
<surname><![CDATA[Rousseau]]></surname>
<given-names><![CDATA[L. M.]]></given-names>
</name>
<name>
<surname><![CDATA[Stergiou]]></surname>
<given-names><![CDATA[K.]]></given-names>
</name>
</person-group>
<source><![CDATA[Integration of Constraint Programming, Artificial Intelligence, and Operations Research. CPAIOR 2019]]></source>
<year>2019</year>
<volume>11494</volume>
<page-range>39-56</page-range></nlm-citation>
</ref>
<ref id="B7">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Bergstra]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Bardenet]]></surname>
<given-names><![CDATA[R.]]></given-names>
</name>
<name>
<surname><![CDATA[Bengio]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
<name>
<surname><![CDATA[Kégl]]></surname>
<given-names><![CDATA[B.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Algorithms for hyper-parameter optimization]]></article-title>
<source><![CDATA[Advances in Neural Information Processing Systems]]></source>
<year>2011</year>
<volume>24</volume>
</nlm-citation>
</ref>
<ref id="B8">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Cho]]></surname>
<given-names><![CDATA[K.]]></given-names>
</name>
<name>
<surname><![CDATA[van-Merriënboer]]></surname>
<given-names><![CDATA[B.]]></given-names>
</name>
<name>
<surname><![CDATA[Gulcehre]]></surname>
<given-names><![CDATA[C.]]></given-names>
</name>
<name>
<surname><![CDATA[Bahdanau]]></surname>
<given-names><![CDATA[D.]]></given-names>
</name>
<name>
<surname><![CDATA[Bougares]]></surname>
<given-names><![CDATA[F.]]></given-names>
</name>
<name>
<surname><![CDATA[Schwenk]]></surname>
<given-names><![CDATA[H.]]></given-names>
</name>
<name>
<surname><![CDATA[Bengio]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
</person-group>
<source><![CDATA[Learning phrase representations using RNN encoder-decoder for statistical machine translation]]></source>
<year>2014</year>
<conf-name><![CDATA[ Conference on Empirical Methods in Natural Language Processing (EMNLP)]]></conf-name>
<conf-date>2014</conf-date>
<conf-loc> </conf-loc>
</nlm-citation>
</ref>
<ref id="B9">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Davies]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
</person-group>
<source><![CDATA[Solving MaxSAT by decoupling optimization and satisfaction]]></source>
<year>2013</year>
<publisher-name><![CDATA[University of Toronto]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B10">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Demirovic]]></surname>
<given-names><![CDATA[E.]]></given-names>
</name>
<name>
<surname><![CDATA[Musliu]]></surname>
<given-names><![CDATA[N.]]></given-names>
</name>
</person-group>
<source><![CDATA[Modeling high school timetabling as partial weighted maxSAT]]></source>
<year>2014</year>
<conf-name><![CDATA[ LaSh 2014: The 4th Workshop on Logic and Search]]></conf-name>
<conf-loc> </conf-loc>
<page-range>1-39</page-range></nlm-citation>
</ref>
<ref id="B11">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Demirovic]]></surname>
<given-names><![CDATA[E.]]></given-names>
</name>
<name>
<surname><![CDATA[Musliu]]></surname>
<given-names><![CDATA[N.]]></given-names>
</name>
<name>
<surname><![CDATA[Winter]]></surname>
<given-names><![CDATA[F.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Modeling and solving staff scheduling with partial weighted maxSAT]]></article-title>
<source><![CDATA[Annals of Operations Research]]></source>
<year>2019</year>
<volume>275</volume>
<page-range>79-99</page-range></nlm-citation>
</ref>
<ref id="B12">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Graves]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
</person-group>
<source><![CDATA[Generating sequences with recurrent neural networks]]></source>
<year>2013</year>
</nlm-citation>
</ref>
<ref id="B13">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Grover]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Leskovec]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
</person-group>
<source><![CDATA[node2vec: Scalable feature learning for networks]]></source>
<year>2016</year>
<conf-name><![CDATA[ 22nd ACM SIGKDD International Conference on Knowledge discovery and data mining]]></conf-name>
<conf-loc> </conf-loc>
<page-range>855-64</page-range></nlm-citation>
</ref>
<ref id="B14">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Hochreiter]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Schmidhuber]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Long short-term memory]]></article-title>
<source><![CDATA[Neural computation]]></source>
<year>1997</year>
<volume>9</volume>
<numero>8</numero>
<issue>8</issue>
<page-range>1735-80</page-range></nlm-citation>
</ref>
<ref id="B15">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Hottung]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Kwon]]></surname>
<given-names><![CDATA[Y. D.]]></given-names>
</name>
<name>
<surname><![CDATA[Tierney]]></surname>
<given-names><![CDATA[K.]]></given-names>
</name>
</person-group>
<source><![CDATA[Efficient active search for combinatorial optimization problems]]></source>
<year>2021</year>
<conf-name><![CDATA[ The International Conference on Learning Representations]]></conf-name>
<conf-date>2022</conf-date>
<conf-loc> </conf-loc>
</nlm-citation>
</ref>
<ref id="B16">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Juma]]></surname>
<given-names><![CDATA[F.]]></given-names>
</name>
<name>
<surname><![CDATA[Hsu]]></surname>
<given-names><![CDATA[E. I.]]></given-names>
</name>
<name>
<surname><![CDATA[McIlraith]]></surname>
<given-names><![CDATA[S. A.]]></given-names>
</name>
</person-group>
<source><![CDATA[Preference-based planning via MaxSAT]]></source>
<year>2012</year>
<volume>7310</volume>
<conf-name><![CDATA[ Advances in Artificial Intelligence: 25th Canadian Conference on Artificial Intelligence]]></conf-name>
<conf-loc> </conf-loc>
<page-range>109-20</page-range></nlm-citation>
</ref>
<ref id="B17">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Khalil]]></surname>
<given-names><![CDATA[E.]]></given-names>
</name>
<name>
<surname><![CDATA[Dai]]></surname>
<given-names><![CDATA[H.]]></given-names>
</name>
<name>
<surname><![CDATA[Zhang]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
<name>
<surname><![CDATA[Dilkina]]></surname>
<given-names><![CDATA[B.]]></given-names>
</name>
<name>
<surname><![CDATA[Song]]></surname>
<given-names><![CDATA[L.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Learning combinatorial optimization algorithms over graphs]]></article-title>
<source><![CDATA[Advances in Neural Information Processing Systems]]></source>
<year>2017</year>
<volume>30</volume>
</nlm-citation>
</ref>
<ref id="B18">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Kingma]]></surname>
<given-names><![CDATA[D. P.]]></given-names>
</name>
<name>
<surname><![CDATA[Ba]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
</person-group>
<source><![CDATA[Adam: A method for stochastic optimization]]></source>
<year>2014</year>
<conf-name><![CDATA[ International Conference on Learning Representations]]></conf-name>
<conf-loc> </conf-loc>
</nlm-citation>
</ref>
<ref id="B19">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Kool]]></surname>
<given-names><![CDATA[W.]]></given-names>
</name>
<name>
<surname><![CDATA[van-Hoof]]></surname>
<given-names><![CDATA[H.]]></given-names>
</name>
<name>
<surname><![CDATA[Welling]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
</person-group>
<source><![CDATA[Attention, learn to solve routing problems!]]></source>
<year>2018</year>
<conf-name><![CDATA[ International Conference on Learning Representations]]></conf-name>
<conf-date>2019</conf-date>
<conf-loc> </conf-loc>
</nlm-citation>
</ref>
<ref id="B20">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Li]]></surname>
<given-names><![CDATA[L.]]></given-names>
</name>
<name>
<surname><![CDATA[Jamieson]]></surname>
<given-names><![CDATA[K.]]></given-names>
</name>
<name>
<surname><![CDATA[Rostamizadeh]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Gonina]]></surname>
<given-names><![CDATA[K.]]></given-names>
</name>
<name>
<surname><![CDATA[Hardt]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Recht]]></surname>
<given-names><![CDATA[B.]]></given-names>
</name>
<name>
<surname><![CDATA[Talwalkar]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
</person-group>
<source><![CDATA[Massively parallel hyperparameter tuning]]></source>
<year>2018</year>
<conf-name><![CDATA[ ICLR 2018 Conference Acceptance Decision]]></conf-name>
<conf-loc> </conf-loc>
</nlm-citation>
</ref>
<ref id="B21">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Liaw]]></surname>
<given-names><![CDATA[R.]]></given-names>
</name>
<name>
<surname><![CDATA[Liang]]></surname>
<given-names><![CDATA[E.]]></given-names>
</name>
<name>
<surname><![CDATA[Nishihara]]></surname>
<given-names><![CDATA[R.]]></given-names>
</name>
<name>
<surname><![CDATA[Moritz]]></surname>
<given-names><![CDATA[P.]]></given-names>
</name>
<name>
<surname><![CDATA[Gonzalez]]></surname>
<given-names><![CDATA[J. E.]]></given-names>
</name>
<name>
<surname><![CDATA[Stoica]]></surname>
<given-names><![CDATA[I.]]></given-names>
</name>
</person-group>
<source><![CDATA[Tune: A research platform for distributed model selection and training]]></source>
<year>2018</year>
</nlm-citation>
</ref>
<ref id="B22">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Martins]]></surname>
<given-names><![CDATA[R.]]></given-names>
</name>
<name>
<surname><![CDATA[Manquinho]]></surname>
<given-names><![CDATA[V.]]></given-names>
</name>
<name>
<surname><![CDATA[Lynce]]></surname>
<given-names><![CDATA[I.]]></given-names>
</name>
</person-group>
<source><![CDATA[Open-WBO: A modular MaxSAT solver]]></source>
<year>2014</year>
<conf-name><![CDATA[ Theory and Applications of Satisfiability Testing&#8211;SAT 2014: 17th International Conference, Held as Part of the Vienna Summer of Logic, VSL]]></conf-name>
<conf-date>2014</conf-date>
<conf-loc> </conf-loc>
<page-range>438-45</page-range></nlm-citation>
</ref>
<ref id="B23">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Martins]]></surname>
<given-names><![CDATA[R.]]></given-names>
</name>
<name>
<surname><![CDATA[Manthey]]></surname>
<given-names><![CDATA[N.]]></given-names>
</name>
<name>
<surname><![CDATA[Terra-Neves]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Manquinho]]></surname>
<given-names><![CDATA[V.]]></given-names>
</name>
<name>
<surname><![CDATA[Lynce]]></surname>
<given-names><![CDATA[I.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Open-WBO @ MaxSAT evaluation 2023]]></article-title>
<source><![CDATA[MaxSAT Evaluation 2023]]></source>
<year>2023</year>
<page-range>18-9</page-range></nlm-citation>
</ref>
<ref id="B24">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Safarpour]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Mangassarian]]></surname>
<given-names><![CDATA[H.]]></given-names>
</name>
<name>
<surname><![CDATA[Veneris]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Liffiton]]></surname>
<given-names><![CDATA[M. H.]]></given-names>
</name>
<name>
<surname><![CDATA[Sakallah]]></surname>
<given-names><![CDATA[K. A.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Improved design debugging using maximum satisfiability]]></article-title>
<source><![CDATA[Formal Methods in Computer Aided Design]]></source>
<year>2007</year>
<page-range>13-9</page-range></nlm-citation>
</ref>
<ref id="B25">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Selsam]]></surname>
<given-names><![CDATA[D.]]></given-names>
</name>
<name>
<surname><![CDATA[Lamm]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Bünz]]></surname>
<given-names><![CDATA[B.]]></given-names>
</name>
<name>
<surname><![CDATA[Liang]]></surname>
<given-names><![CDATA[P.]]></given-names>
</name>
<name>
<surname><![CDATA[de-Moura]]></surname>
<given-names><![CDATA[L.]]></given-names>
</name>
<name>
<surname><![CDATA[Dill]]></surname>
<given-names><![CDATA[D. L.]]></given-names>
</name>
</person-group>
<source><![CDATA[Learning a SAT solver from single-bit supervision]]></source>
<year>2018</year>
</nlm-citation>
</ref>
<ref id="B26">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Vaswani]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Shazeer]]></surname>
<given-names><![CDATA[N.]]></given-names>
</name>
<name>
<surname><![CDATA[Parmar]]></surname>
<given-names><![CDATA[N.]]></given-names>
</name>
<name>
<surname><![CDATA[Uszkoreit]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Jones]]></surname>
<given-names><![CDATA[L.]]></given-names>
</name>
<name>
<surname><![CDATA[Gomez]]></surname>
<given-names><![CDATA[A. N.]]></given-names>
</name>
<name>
<surname><![CDATA[Kaiser]]></surname>
<given-names><![CDATA[L.]]></given-names>
</name>
<name>
<surname><![CDATA[Polosukhin]]></surname>
<given-names><![CDATA[I.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Attention is all you need]]></article-title>
<source><![CDATA[Advances in Neural Information Processing Systems]]></source>
<year>2017</year>
<volume>30</volume>
</nlm-citation>
</ref>
<ref id="B27">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Williams]]></surname>
<given-names><![CDATA[R. J.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Simple statistical gradient-following algorithms for connectionist reinforcement learning]]></article-title>
<source><![CDATA[Machine learning]]></source>
<year>1992</year>
<volume>8</volume>
<page-range>229-56</page-range></nlm-citation>
</ref>
</ref-list>
</back>
</article>
