{"id":"https://openalex.org/W2115714256","doi":"https://doi.org/10.1109/asru.2009.5373413","title":"Representing the Reinforcement Learning state in a negotiation dialogue","display_name":"Representing the Reinforcement Learning state in a negotiation dialogue","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2115714256","doi":"https://doi.org/10.1109/asru.2009.5373413","mag":"2115714256"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2009.5373413","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373413","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","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/A5046590019","display_name":"Peter A. Heeman","orcid":null},"institutions":[{"id":"https://openalex.org/I165690674","display_name":"Oregon Health & Science University","ror":"https://ror.org/009avj582","country_code":"US","type":"education","lineage":["https://openalex.org/I165690674"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Peter A. Heeman","raw_affiliation_strings":["Center for Spoken Language Understanding, Oregon Health and Sciences University, Beaverton, OR, USA","Center for Spoken Language Understanding, Oregon Health & Science University, Beaverton OR, 97006, USA"],"affiliations":[{"raw_affiliation_string":"Center for Spoken Language Understanding, Oregon Health and Sciences University, Beaverton, OR, USA","institution_ids":[]},{"raw_affiliation_string":"Center for Spoken Language Understanding, Oregon Health & Science University, Beaverton OR, 97006, USA","institution_ids":["https://openalex.org/I165690674"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5046590019"],"corresponding_institution_ids":["https://openalex.org/I165690674"],"apc_list":null,"apc_paid":null,"fwci":1.8065,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.87850002,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"3","issue":null,"first_page":"450","last_page":"455"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":1.0,"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/T12031","display_name":"Speech and dialogue systems","score":1.0,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9980000257492065,"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":0.9440289735794067},{"id":"https://openalex.org/keywords/negotiation","display_name":"Negotiation","score":0.8468692898750305},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8146327137947083},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7354444265365601},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5625773668289185},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5308262705802917},{"id":"https://openalex.org/keywords/information-exchange","display_name":"Information exchange","score":0.4885176420211792},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4820621609687805},{"id":"https://openalex.org/keywords/track","display_name":"Track (disk drive)","score":0.481766939163208},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.4289221465587616},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.42521852254867554},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.4249136447906494},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.41211605072021484},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3603571653366089},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2406555414199829},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09227195382118225},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08190158009529114},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.0724259614944458}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9440289735794067},{"id":"https://openalex.org/C199776023","wikidata":"https://www.wikidata.org/wiki/Q202875","display_name":"Negotiation","level":2,"score":0.8468692898750305},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8146327137947083},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7354444265365601},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5625773668289185},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5308262705802917},{"id":"https://openalex.org/C189693848","wikidata":"https://www.wikidata.org/wiki/Q6031064","display_name":"Information exchange","level":2,"score":0.4885176420211792},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4820621609687805},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.481766939163208},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.4289221465587616},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.42521852254867554},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.4249136447906494},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.41211605072021484},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3603571653366089},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2406555414199829},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09227195382118225},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08190158009529114},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0724259614944458},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/asru.2009.5373413","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373413","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.157.5282","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.157.5282","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-internal.cse.ogi.edu/~heeman/papers/09-asru.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":0.5699999928474426}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W13088146","https://openalex.org/W16069229","https://openalex.org/W160067033","https://openalex.org/W1681299129","https://openalex.org/W2001050921","https://openalex.org/W2062244797","https://openalex.org/W2083205357","https://openalex.org/W2101308260","https://openalex.org/W2121528300","https://openalex.org/W2132997613","https://openalex.org/W2143691865","https://openalex.org/W2148249921","https://openalex.org/W2159581299","https://openalex.org/W2791590751","https://openalex.org/W3099293669","https://openalex.org/W6683739010"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W2126211886","https://openalex.org/W2928233854"],"abstract_inverted_index":{"Most":[0],"applications":[1],"of":[2,72,132],"reinforcement":[3],"learning":[4],"(RL)":[5],"for":[6,118],"dialogue":[7],"have":[8],"focused":[9],"on":[10,34],"slot-filling":[11],"tasks.":[12],"In":[13,92],"this":[14,93,109],"paper,":[15],"we":[16,95],"explore":[17],"a":[18,35,115,124,128],"task":[19],"that":[20,51,60,75,101,108],"requires":[21],"negotiation,":[22],"in":[23,30,45,66,89],"which":[24],"conversants":[25],"need":[26],"to":[27,32,83,113,127,135],"exchange":[28],"information":[29,41],"order":[31],"decide":[33],"good":[36,116],"solution.":[37],"We":[38,68,106],"investigate":[39],"what":[40],"should":[42],"be":[43,56],"included":[44],"the":[46,61,73,76,85,90,99,102,119],"system's":[47,86],"RL":[48,134],"state":[49,62],"so":[50,59],"an":[52],"optimal":[53],"policy":[54,117],"can":[55,96],"learned":[57],"and":[58,80],"space":[63],"stays":[64],"reasonable":[65],"size.":[67],"propose":[69],"keeping":[70],"track":[71],"decisions":[74],"system":[77,103],"has":[78],"made,":[79],"using":[81],"them":[82],"constrain":[84],"future":[87],"behavior":[88],"dialogue.":[91],"way,":[94],"compositionally":[97],"represent":[98],"strategy":[100],"is":[104,111,123],"employing.":[105],"show":[107],"approach":[110],"able":[112],"learn":[114],"task.":[120],"This":[121],"work":[122],"first":[125],"step":[126],"more":[129],"general":[130],"exploration":[131],"applying":[133],"negotiation":[136],"dialogues.":[137]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}