{"id":"https://openalex.org/W72400652","doi":null,"title":"Multiple-goal reinforcement learning with modular Sarsa(O)","display_name":"Multiple-goal reinforcement learning with modular Sarsa(O)","publication_year":2003,"publication_date":"2003-08-09","ids":{"openalex":"https://openalex.org/W72400652","mag":"72400652"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.163.2453","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.163.2453","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ijcai.org/Past%20Proceedings/IJCAI-2003/PDF/233.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5089617051","display_name":"Nathan R. Sprague","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathan Sprague","raw_affiliation_strings":["[Computer Science Department, University of Rochester, Rochester, NY]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"[Computer Science Department, University of Rochester, Rochester, NY]","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103584849","display_name":"Dana H. Ballard","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dana H. Ballard","raw_affiliation_strings":["[Computer Science Department, University of Rochester, Rochester, NY]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"[Computer Science Department, University of Rochester, Rochester, NY]","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I5388228"],"apc_list":null,"apc_paid":null,"fwci":2.7752,"has_fulltext":false,"cited_by_count":95,"citation_normalized_percentile":{"value":0.90018547,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1445","last_page":"1447"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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/T10462","display_name":"Reinforcement Learning in Robotics","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/T12072","display_name":"Machine Learning and Algorithms","score":0.0,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/joint-action","display_name":"joint action","score":0.5130000114440918},{"id":"https://openalex.org/keywords/goal-directed-learning","display_name":"goal-directed learning","score":0.39500001072883606}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9136450290679932},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8380011916160583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7192401885986328},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6454924941062927},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.634742796421051},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6161141991615295},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5872972011566162},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5453543066978455},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.44949811697006226},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44203874468803406},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4102935791015625},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.374447762966156},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14740276336669922},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1170976459980011},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural 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},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":8,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.163.2453","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.163.2453","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ijcai.org/Past%20Proceedings/IJCAI-2003/PDF/233.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.4.3660","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.4.3660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.rochester.edu/research/vision/pubs/2003/Sprague_Multiple_Goal_RL_IJCAI_2003/Sprague_Multiple_Goal_RL_IJCAI_2003.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.69.4408","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.69.4408","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://max.cs.kzoo.edu/~nsprague/papers/ijcai03-tr.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.73.558","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.73.558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://max.cs.kzoo.edu/~nsprague/papers/ijcai03.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.76.4059","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.76.4059","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.rochester.edu/research/vision/pubs/2003/Sprague_Multiple_Goal_RL_IJCAI_2003/Sprague_Multiple_Goal_RL_IJCAI_2003.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.9.7282","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.9.7282","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://ftp.cs.rochester.edu/pub/papers/robotics/03.tr798.Mult_goal_reinforcement_learning_with_modular_Sarsa0.ps.gz","raw_type":"text"},{"id":"pmh:oai:urresearch.rochester.edu:222","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/1802/339","pdf_url":null,"source":{"id":"https://openalex.org/S4306400518","display_name":"UR Research (University of Rochester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I5388228","host_organization_name":"University of Rochester","host_organization_lineage":["https://openalex.org/I5388228"],"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":"Technical Report"},{"id":"mag:72400652","doi":null,"is_oa":false,"landing_page_url":"http://ijcai.org/Past%20Proceedings/IJCAI-2003/PDF/233.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Joint Conference on Artificial Intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W6242441","https://openalex.org/W24785488","https://openalex.org/W1480676279","https://openalex.org/W2113913482","https://openalex.org/W2114958204","https://openalex.org/W2121517924","https://openalex.org/W2124175081","https://openalex.org/W2126566174","https://openalex.org/W2129307307","https://openalex.org/W2137466452","https://openalex.org/W2147492008","https://openalex.org/W2150339816","https://openalex.org/W3139377883"],"related_works":["https://openalex.org/W6993026462","https://openalex.org/W2354212205","https://openalex.org/W4402267418","https://openalex.org/W3028466545","https://openalex.org/W2189549406","https://openalex.org/W7100586887","https://openalex.org/W24785488","https://openalex.org/W6922792536","https://openalex.org/W7101001091","https://openalex.org/W7100078473"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,65,94],"new":[3],"algorithm,":[4],"GM-Sarsa(0),":[5],"for":[6,56,67,100,103],"finding":[7,53],"approximate":[8],"solutions":[9],"to":[10,24],"multiple-goal":[11],"reinforcement":[12,44],"learning":[13,45],"problems":[14],"that":[15,33,39,77,79],"are":[16,29,34,80,91],"modeled":[17,30],"as":[18,31],"composite":[19,69,95,119],"Markov":[20],"decision":[21],"processes.":[22],"According":[23],"our":[25,109],"formulation":[26],"di#erent":[27],"sub-goals":[28],"MDPs":[32,106],"coupled":[35],"by":[36,51],"the":[37,57,68,104,115,118],"requirement":[38],"they":[40,90],"share":[41],"actions.":[42],"Existing":[43],"algorithms":[46],"address":[47],"similar":[48],"problem":[49,72],"formulations":[50],"first":[52],"optimal":[54,101],"policies":[55,78,102,113],"component":[58,105],"MDPs,":[59],"and":[60],"then":[61],"merging":[62],"these":[63],"into":[64,93],"policy":[66],"task.":[70,120],"The":[71],"with":[73],"such":[74],"methods":[75],"is":[76],"optimized":[81],"separately":[82],"may":[83,85],"or":[84],"not":[86],"perform":[87],"well":[88],"when":[89],"merged":[92],"solution.":[96],"Instead":[97],"of":[98,117],"searching":[99],"in":[107,114],"isolation,":[108],"approach":[110],"finds":[111],"good":[112],"context":[116]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":2}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2016-06-24T00:00:00"}