{"id":"https://openalex.org/W2024372657","doi":"https://doi.org/10.1145/1160633.1160773","title":"Rule value reinforcement learning for cognitive agents","display_name":"Rule value reinforcement learning for cognitive agents","publication_year":2006,"publication_date":"2006-05-08","ids":{"openalex":"https://openalex.org/W2024372657","doi":"https://doi.org/10.1145/1160633.1160773","mag":"2024372657"},"language":"en","primary_location":{"id":"doi:10.1145/1160633.1160773","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1160633.1160773","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fifth international joint conference on Autonomous agents and multiagent systems","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064657398","display_name":"Chris Child","orcid":"https://orcid.org/0000-0001-5425-2308"},"institutions":[{"id":"https://openalex.org/I180825142","display_name":"City, University of London","ror":"https://ror.org/04489at23","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I180825142"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chris Child","raw_affiliation_strings":["City University, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University, London, UK","institution_ids":["https://openalex.org/I180825142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035046930","display_name":"Kostas Stathis","orcid":"https://orcid.org/0000-0002-9946-4037"},"institutions":[{"id":"https://openalex.org/I180825142","display_name":"City, University of London","ror":"https://ror.org/04489at23","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I180825142"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kostas Stathis","raw_affiliation_strings":["City University, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University, London, UK","institution_ids":["https://openalex.org/I180825142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I180825142"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"792","last_page":"794"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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":0.9988999962806702,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9965000152587891,"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/T10320","display_name":"Neural Networks and Applications","score":0.9907000064849854,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.904263973236084},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7038439512252808},{"id":"https://openalex.org/keywords/percept","display_name":"Percept","score":0.6624549031257629},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6160241961479187},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5931969285011292},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.563386857509613},{"id":"https://openalex.org/keywords/situated","display_name":"Situated","score":0.5417500138282776},{"id":"https://openalex.org/keywords/learning-rule","display_name":"Learning rule","score":0.46343809366226196},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.45768749713897705},{"id":"https://openalex.org/keywords/rule-based-system","display_name":"Rule-based system","score":0.4546840190887451},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4440959692001343},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4440813660621643},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.44150346517562866},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43618014454841614},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.4290426969528198},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.14992401003837585},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09030765295028687},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.08794131875038147}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.904263973236084},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7038439512252808},{"id":"https://openalex.org/C2779687425","wikidata":"https://www.wikidata.org/wiki/Q7166998","display_name":"Percept","level":3,"score":0.6624549031257629},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6160241961479187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5931969285011292},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.563386857509613},{"id":"https://openalex.org/C132829578","wikidata":"https://www.wikidata.org/wiki/Q581151","display_name":"Situated","level":2,"score":0.5417500138282776},{"id":"https://openalex.org/C2779127903","wikidata":"https://www.wikidata.org/wiki/Q6510194","display_name":"Learning rule","level":3,"score":0.46343809366226196},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.45768749713897705},{"id":"https://openalex.org/C149271511","wikidata":"https://www.wikidata.org/wiki/Q1417149","display_name":"Rule-based system","level":2,"score":0.4546840190887451},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4440959692001343},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4440813660621643},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.44150346517562866},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43618014454841614},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.4290426969528198},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.14992401003837585},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09030765295028687},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.08794131875038147},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1160633.1160773","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1160633.1160773","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fifth international joint conference on Autonomous agents and multiagent systems","raw_type":"proceedings-article"},{"id":"pmh:oai:openaccess.city.ac.uk:3001","is_oa":false,"landing_page_url":"https://openaccess.city.ac.uk/view/creators_id/c=2Echild.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4306401940","display_name":"City Research Online (City University London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I180825142","host_organization_name":"City, University of London","host_organization_lineage":["https://openalex.org/I180825142"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1505285649","https://openalex.org/W1515851193","https://openalex.org/W1925600676","https://openalex.org/W2121863487","https://openalex.org/W2157117634","https://openalex.org/W3011120880"],"related_works":["https://openalex.org/W2766258251","https://openalex.org/W812515830","https://openalex.org/W3140225428","https://openalex.org/W235959167","https://openalex.org/W2610686804","https://openalex.org/W3148138296","https://openalex.org/W2313756439","https://openalex.org/W4210374076","https://openalex.org/W2141149254","https://openalex.org/W1987864653"],"abstract_inverted_index":{"RVRL":[0],"(Rule":[1],"Value":[2],"Reinforcement":[3],"Learning)":[4],"is":[5,44],"a":[6,20,24,48,82],"new":[7,75],"algorithm":[8,29],"which":[9],"extends":[10],"an":[11,59],"existing":[12],"learning":[13],"framework":[14,76],"that":[15],"models":[16],"the":[17,42,55,62,68,74],"environment":[18],"of":[19,57,73],"situated":[21],"agent":[22],"using":[23],"probabilistic":[25],"rule":[26,52],"representation.":[27],"The":[28,50],"attaches":[30],"values":[31,53],"to":[32,46],"learned":[33],"rules":[34,43],"by":[35,41],"adapting":[36],"reinforcement":[37],"learning.":[38],"Structure":[39],"captured":[40],"used":[45],"form":[47],"policy.":[49],"resulting":[51],"represent":[54],"utility":[56],"taking":[58],"action":[60],"if":[61],"rule's":[63],"conditions":[64],"are":[65,77],"present":[66],"in":[67,81],"agent's":[69],"current":[70],"percept.":[71],"Advantages":[72],"demonstrated,":[78],"through":[79],"examples":[80],"predator-prey":[83],"environment.":[84]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}