{"id":"https://openalex.org/W2111572265","doi":"https://doi.org/10.1145/1143844.1143851","title":"Relational temporal difference learning","display_name":"Relational temporal difference learning","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2111572265","doi":"https://doi.org/10.1145/1143844.1143851","mag":"2111572265"},"language":"en","primary_location":{"id":"doi:10.1145/1143844.1143851","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1143844.1143851","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international conference on Machine learning  - ICML '06","raw_type":"proceedings-article"},"type":"article","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/A5070174321","display_name":"Nima Asgharbeygi","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nima Asgharbeygi","raw_affiliation_strings":["Stanford University, Stanford, CA","Stanford University Stanford CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University Stanford CA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043938358","display_name":"David John Stracuzzi","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Stracuzzi","raw_affiliation_strings":["Stanford University, Stanford, CA","Stanford University Stanford CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University Stanford CA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081275482","display_name":"Pat Langley","orcid":"https://orcid.org/0000-0001-5260-7048"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pat Langley","raw_affiliation_strings":["Stanford University, Stanford, CA","Stanford University Stanford CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University Stanford CA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3314,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.89574407,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"49","last_page":"56"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9868999719619751,"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":0.9768999814987183,"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/computer-science","display_name":"Computer science","score":0.6673735976219177},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.388129860162735}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6673735976219177},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.388129860162735}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1143844.1143851","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1143844.1143851","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international conference on Machine learning  - ICML '06","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.154.9765","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.154.9765","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.74.3343","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.74.3343","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://imls.engr.oregonstate.edu/www/htdocs/proceedings/icml2006/007_Relational_Temporal.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.800000011920929}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W16011919","https://openalex.org/W134602879","https://openalex.org/W1512592747","https://openalex.org/W1515851193","https://openalex.org/W1531285229","https://openalex.org/W1542941925","https://openalex.org/W1600246594","https://openalex.org/W1800916125","https://openalex.org/W2038812321","https://openalex.org/W2041367235","https://openalex.org/W2089415692","https://openalex.org/W2107726111","https://openalex.org/W2121517924","https://openalex.org/W2121863487","https://openalex.org/W2128361632","https://openalex.org/W2134153324","https://openalex.org/W2138289776","https://openalex.org/W2154441654","https://openalex.org/W2396715201","https://openalex.org/W2521075165","https://openalex.org/W3020831056"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2093578348","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2766271392","https://openalex.org/W2350741829","https://openalex.org/W3107474891"],"abstract_inverted_index":{"We":[0,40,66],"introduce":[1],"relational":[2,38],"temporal":[3,23],"difference":[4,24],"learning":[5,61],"as":[6],"an":[7],"effective":[8],"approach":[9],"to":[10,26],"solving":[11],"multi-agent":[12],"Markov":[13],"decision":[14],"problems":[15],"with":[16],"large":[17],"state":[18],"spaces.":[19],"Our":[20],"algorithm":[21],"uses":[22],"reinforcement":[25],"learn":[27],"a":[28,34],"distributed":[29],"value":[30],"function":[31],"represented":[32],"over":[33],"conceptual":[35],"hierarchy":[36],"of":[37],"predicates.":[39],"present":[41],"experiments":[42],"using":[43],"two":[44],"domains":[45],"from":[46],"the":[47],"General":[48],"Game":[49],"Playing":[50],"repository,":[51],"in":[52],"which":[53],"we":[54],"observe":[55],"that":[56],"our":[57],"system":[58],"achieves":[59],"higher":[60],"rates":[62],"than":[63],"non-relational":[64],"methods.":[65],"also":[67],"discuss":[68],"related":[69],"work":[70],"and":[71],"directions":[72],"for":[73],"future":[74],"research.":[75]},"counts_by_year":[{"year":2020,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}