{"id":"https://openalex.org/W2127257142","doi":null,"title":"Policy Search Based Relational Reinforcement Learning using the Cross-Entropy Method","display_name":"Policy Search Based Relational Reinforcement Learning using the Cross-Entropy Method","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W2127257142","mag":"2127257142"},"language":"en","primary_location":{"id":"pmh:oai:researchcommons.waikato.ac.nz:10289/7671","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/10289/7671","pdf_url":"https://hdl.handle.net/10289/7671","source":{"id":"https://openalex.org/S7407063277","display_name":"Research Commons (University of Waikato)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/10289/7671","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005207564","display_name":"Samuel Sarjant","orcid":"https://orcid.org/0000-0002-9478-5835","observed_orcids":["https://orcid.org/0000-0002-9478-5835"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Samuel Sarjant","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-9478-5835","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5005207564"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/relational-reinforcement-learning","display_name":"relational reinforcement learning","score":0.9990000128746033},{"id":"https://openalex.org/keywords/cross-entropy-method","display_name":"cross-entropy method","score":0.8700000047683716},{"id":"https://openalex.org/keywords/policy-search","display_name":"policy search","score":0.9319999814033508},{"id":"https://openalex.org/keywords/condition-action-rules","display_name":"condition-action rules","score":0.8830000162124634},{"id":"https://openalex.org/keywords/relational-representation","display_name":"relational representation","score":0.5220000147819519},{"id":"https://openalex.org/keywords/rule-simplification","display_name":"rule simplification","score":0.921999990940094},{"id":"https://openalex.org/keywords/infinite-state-spaces","display_name":"infinite state spaces","score":0.4970000088214874}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7301048040390015},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.667780339717865},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.6203891634941101},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5378823280334473},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4843515157699585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4738895297050476},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4701027274131775},{"id":"https://openalex.org/C177877439","wikidata":"https://www.wikidata.org/wiki/Q7604413","display_name":"Statistical relational learning","level":3,"score":0.435389906167984},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.41050171852111816},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3567661643028259},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.29734739661216736},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2689230442047119},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19285133481025696},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.07796752452850342},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:researchcommons.waikato.ac.nz:10289/7671","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/10289/7671","pdf_url":"https://hdl.handle.net/10289/7671","source":{"id":"https://openalex.org/S7407063277","display_name":"Research Commons (University of Waikato)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},{"id":"mag:2127257142","doi":null,"is_oa":false,"landing_page_url":"https://researchcommons.waikato.ac.nz/bitstream/handle/10289/7671/thesis.pdf;sequence=7","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:researchcommons.waikato.ac.nz:10289/7671","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/10289/7671","pdf_url":"https://hdl.handle.net/10289/7671","source":{"id":"https://openalex.org/S7407063277","display_name":"Research Commons (University of Waikato)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310144","display_name":"Tertiary Education Commission","ror":"https://ror.org/05xhe5a74"},{"id":"https://openalex.org/F4320311746","display_name":"University of Waikato","ror":"https://ror.org/013fsnh78"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2127257142.pdf","grobid_xml":"https://content.openalex.org/works/W2127257142.grobid-xml"},"referenced_works_count":145,"referenced_works":["https://openalex.org/W14624541","https://openalex.org/W28386172","https://openalex.org/W30507863","https://openalex.org/W32403112","https://openalex.org/W42392872","https://openalex.org/W46258415","https://openalex.org/W47380661","https://openalex.org/W86212350","https://openalex.org/W87548251","https://openalex.org/W106493965","https://openalex.org/W108687325","https://openalex.org/W124234194","https://openalex.org/W131663416","https://openalex.org/W145490631","https://openalex.org/W146724768","https://openalex.org/W169477153","https://openalex.org/W1482627017","https://openalex.org/W1490954610","https://openalex.org/W1495789285","https://openalex.org/W1497256448","https://openalex.org/W1511354083","https://openalex.org/W1512838955","https://openalex.org/W1533597678","https://openalex.org/W1536655300","https://openalex.org/W1541434994","https://openalex.org/W1550698229","https://openalex.org/W1565236324","https://openalex.org/W1569963244","https://openalex.org/W1574001572","https://openalex.org/W1576452626","https://openalex.org/W1580563784","https://openalex.org/W1582046617","https://openalex.org/W1583833196","https://openalex.org/W1585067080","https://openalex.org/W1608608607","https://openalex.org/W1626155273","https://openalex.org/W1628056908","https://openalex.org/W1639032689","https://openalex.org/W1640646391","https://openalex.org/W1654728867","https://openalex.org/W1700914952","https://openalex.org/W1749523692","https://openalex.org/W1760997490","https://openalex.org/W1761227569","https://openalex.org/W1778554682","https://openalex.org/W1914583973","https://openalex.org/W1965555277","https://openalex.org/W1980035368","https://openalex.org/W1984948855","https://openalex.org/W1985658808","https://openalex.org/W1989101984","https://openalex.org/W2009303086","https://openalex.org/W2012170877","https://openalex.org/W2028145673","https://openalex.org/W2037199950","https://openalex.org/W2041367235","https://openalex.org/W2048226872","https://openalex.org/W2049287437","https://openalex.org/W2054497239","https://openalex.org/W2054940200","https://openalex.org/W2070183171","https://openalex.org/W2071311198","https://openalex.org/W2073384958","https://openalex.org/W2078226168","https://openalex.org/W2083143894","https://openalex.org/W2095095223","https://openalex.org/W2095671661","https://openalex.org/W2096232175","https://openalex.org/W2096600060","https://openalex.org/W2099587183","https://openalex.org/W2100211715","https://openalex.org/W2100738443","https://openalex.org/W2104641222","https://openalex.org/W2107726111","https://openalex.org/W2107854230","https://openalex.org/W2109722166","https://openalex.org/W2109910161","https://openalex.org/W2111935653","https://openalex.org/W2113475501","https://openalex.org/W2115330428","https://openalex.org/W2115899886","https://openalex.org/W2116038421","https://openalex.org/W2116339921","https://openalex.org/W2116502002","https://openalex.org/W2118916601","https://openalex.org/W2119567691","https://openalex.org/W2119717200","https://openalex.org/W2119831128","https://openalex.org/W2121723232","https://openalex.org/W2121906195","https://openalex.org/W2121993785","https://openalex.org/W2122410182","https://openalex.org/W2123859855","https://openalex.org/W2124125910","https://openalex.org/W2125074935","https://openalex.org/W2125922627","https://openalex.org/W2126565096","https://openalex.org/W2126834960","https://openalex.org/W2126892350","https://openalex.org/W2130005627","https://openalex.org/W2132083787","https://openalex.org/W2132713246","https://openalex.org/W2133130433","https://openalex.org/W2133574354","https://openalex.org/W2133615895","https://openalex.org/W2133632477","https://openalex.org/W2134153324","https://openalex.org/W2136334537","https://openalex.org/W2138178898","https://openalex.org/W2138289776","https://openalex.org/W2148411640","https://openalex.org/W2149043954","https://openalex.org/W2150821861","https://openalex.org/W2152152733","https://openalex.org/W2152475379","https://openalex.org/W2154393523","https://openalex.org/W2154441654","https://openalex.org/W2155027007","https://openalex.org/W2158292827","https://openalex.org/W2158533677","https://openalex.org/W2159283652","https://openalex.org/W2161608691","https://openalex.org/W2162112538","https://openalex.org/W2162813238","https://openalex.org/W2163302320","https://openalex.org/W2164056559","https://openalex.org/W2166798247","https://openalex.org/W2168359464","https://openalex.org/W2169659168","https://openalex.org/W2215418550","https://openalex.org/W2215946058","https://openalex.org/W2396715201","https://openalex.org/W2492778706","https://openalex.org/W2496221789","https://openalex.org/W2520858206","https://openalex.org/W2521075165","https://openalex.org/W2521833123","https://openalex.org/W2794995252","https://openalex.org/W2970208590","https://openalex.org/W3020831056","https://openalex.org/W3028232160","https://openalex.org/W3149838063","https://openalex.org/W4245296547","https://openalex.org/W4298217995","https://openalex.org/W4300511487"],"related_works":["https://openalex.org/W286185234","https://openalex.org/W2145092134","https://openalex.org/W2404608352","https://openalex.org/W7097774835","https://openalex.org/W2521075165","https://openalex.org/W1536655300","https://openalex.org/W1505515950","https://openalex.org/W2133632477","https://openalex.org/W4415950402","https://openalex.org/W7207577615"],"abstract_inverted_index":{"Relational":[0],"Reinforcement":[1],"Learning":[2],"(RRL)":[3],"is":[4,128,175,197,224],"a":[5,12,18,63,82,103,155,247],"subfield":[6],"of":[7,27,51,67,84,118,135,157,251],"machine":[8],"learning":[9,13],"in":[10,122,168,205,239,246],"which":[11],"agent":[14],"seeks":[15],"to":[16,94,144,160,192,199,226],"maximise":[17],"numerical":[19],"reward":[20],"within":[21],"an":[22,48,72,131,146],"environment,":[23],"represented":[24],"as":[25,62],"collections":[26],"objects":[28],"and":[29,106,154,163,171,232,241],"relations,":[30],"by":[31,130],"performing":[32],"actions":[33],"that":[34,77,112,138,190,223],"interact":[35],"with":[36],"the":[37,90,113,136,140,148,209],"environment.":[38,212],"The":[39,98,229],"relational":[40,86,243],"representation":[41,50],"allows":[42],"more":[43,216],"dynamic":[44],"environment":[45,137,183],"states":[46],"than":[47],"attribute-based":[49],"reinforcement":[52],"learning,":[53],"but":[54],"this":[55],"flexibility":[56],"also":[57],"creates":[58,78],"new":[59],"problems":[60],"such":[61,111],"potentially":[64],"infinite":[65],"number":[66],"states.":[68],"This":[69],"thesis":[70],"describes":[71],"RRL":[73,194,211],"algorithm":[74],"named":[75],"Cerrla":[76,174,196],"policies":[79,116,237,244],"directly":[80],"from":[81],"set":[83,156],"learned":[85],"\u201ccondition-action\u201d":[87],"rules":[88,159,231],"using":[89],"Cross-Entropy":[91],"Method":[92],"(CEM)":[93],"control":[95],"policy":[96],"creation.":[97],"CEM":[99],"assigns":[100],"each":[101,182],"rule":[102,165],"sampling":[104],"probability":[105],"gradually":[107],"modifies":[108],"these":[109],"probabilities":[110],"randomly":[114],"sampled":[115],"consist":[117],"\u2018better\u2019":[119],"rules,":[120],"resulting":[121,167],"larger":[123],"rewards":[124],"received.":[125],"Rule":[126],"creation":[127],"guided":[129],"inferred":[132],"partial":[133],"model":[134],"defines:":[139],"minimal":[141],"conditions":[142,151],"needed":[143],"take":[145],"action,":[147],"possible":[149],"specialisation":[150],"per":[152],"rule,":[153],"simplification":[158],"remove":[161],"redundant":[162],"illegal":[164],"conditions,":[166],"compact,":[169],"efficient,":[170],"comprehensible":[172],"policies.":[173],"evaluated":[176],"on":[177,208],"four":[178],"separate":[179],"environments,":[180,218],"where":[181],"has":[184],"several":[185],"different":[186],"goals.":[187],"Results":[188],"show":[189],"compared":[191],"existing":[193],"algorithms,":[195],"able":[198],"learn":[200,221],"equal":[201],"or":[202],"better":[203],"behaviour":[204,222],"less":[206],"time":[207],"standard":[210],"On":[213],"other":[214],"larger,":[215],"complex":[217],"it":[219],"can":[220],"competitive":[225],"specialised":[227],"approaches.":[228],"simplified":[230],"CEM\u2019s":[233],"bias":[234],"towards":[235],"compact":[236],"result":[238],"comprehensive":[240],"effective":[242],"created":[245],"relatively":[248],"short":[249],"amount":[250],"time.":[252]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2016-06-24T00:00:00"}