{"id":"https://openalex.org/W2007866599","doi":"https://doi.org/10.1145/2001858.2001957","title":"Evolution of reward functions for reinforcement learning","display_name":"Evolution of reward functions for reinforcement learning","publication_year":2011,"publication_date":"2011-07-12","ids":{"openalex":"https://openalex.org/W2007866599","doi":"https://doi.org/10.1145/2001858.2001957","mag":"2007866599"},"language":"en","primary_location":{"id":"doi:10.1145/2001858.2001957","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2001858.2001957","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th annual conference companion on Genetic and evolutionary computation","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/A5043572737","display_name":"Scott Niekum","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Niekum","raw_affiliation_strings":["University of Massachusetts, Amherst, MA, USA","University of Massachusetts, Amherst, MA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts, Amherst, MA, USA#TAB#","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044142640","display_name":"Lee Spector","orcid":"https://orcid.org/0000-0001-5299-4797"},"institutions":[{"id":"https://openalex.org/I47631775","display_name":"Hampshire College","ror":"https://ror.org/03pe1mm80","country_code":"US","type":"education","lineage":["https://openalex.org/I47631775"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lee Spector","raw_affiliation_strings":["Hampshire College, Amherst, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hampshire College, Amherst, MA, USA","institution_ids":["https://openalex.org/I47631775"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089808068","display_name":"Andrew G. Barto","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Barto","raw_affiliation_strings":["University of Massachusetts, Amherst, MA, USA","University of Massachusetts, Amherst, MA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts, Amherst, MA, USA#TAB#","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0775,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.91753864,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"177","last_page":"178"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9998999834060669,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9998999834060669,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9954000115394592,"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/T11663","display_name":"Viral Infectious Diseases and Gene Expression in Insects","score":0.9902999997138977,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8742251396179199},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6979354619979858},{"id":"https://openalex.org/keywords/reward-system","display_name":"Reward system","score":0.5469096899032593},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.49788522720336914},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.485606849193573},{"id":"https://openalex.org/keywords/genetic-programming","display_name":"Genetic programming","score":0.4463285803794861},{"id":"https://openalex.org/keywords/adaptive-system","display_name":"Adaptive system","score":0.42312467098236084},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.41829240322113037},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3384353220462799},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.116413414478302},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09094592928886414}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8742251396179199},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6979354619979858},{"id":"https://openalex.org/C143661069","wikidata":"https://www.wikidata.org/wiki/Q670713","display_name":"Reward system","level":2,"score":0.5469096899032593},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.49788522720336914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.485606849193573},{"id":"https://openalex.org/C110332635","wikidata":"https://www.wikidata.org/wiki/Q629498","display_name":"Genetic programming","level":2,"score":0.4463285803794861},{"id":"https://openalex.org/C52970973","wikidata":"https://www.wikidata.org/wiki/Q2497134","display_name":"Adaptive system","level":2,"score":0.42312467098236084},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.41829240322113037},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3384353220462799},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.116413414478302},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09094592928886414},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2001858.2001957","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2001858.2001957","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th annual conference companion on Genetic and evolutionary computation","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1496040402","https://openalex.org/W1515851193","https://openalex.org/W1777239053","https://openalex.org/W1980900887","https://openalex.org/W2014843952","https://openalex.org/W2121863487","https://openalex.org/W2123408238","https://openalex.org/W2136414484","https://openalex.org/W2164424353","https://openalex.org/W2380628422","https://openalex.org/W2592535843","https://openalex.org/W3011120880","https://openalex.org/W4285719527","https://openalex.org/W6775686901"],"related_works":["https://openalex.org/W1562959674","https://openalex.org/W2923653485","https://openalex.org/W2957776456","https://openalex.org/W4361026739","https://openalex.org/W2952472710","https://openalex.org/W4255994452","https://openalex.org/W4372194388","https://openalex.org/W4206669594","https://openalex.org/W4319083788","https://openalex.org/W3022038857"],"abstract_inverted_index":{"The":[0],"reward":[1,32,57],"functions":[2,33,58],"that":[3,18,59,82],"drive":[4],"reinforcement":[5],"learning":[6,61],"systems":[7,20,36],"are":[8,21,97],"generally":[9],"derived":[10],"directly":[11],"from":[12],"the":[13,16,19,49,67,83,88],"descriptions":[14],"of":[15,51,70,90],"problems":[17],"being":[22],"used":[23],"to":[24,37,54,80],"solve.":[25],"In":[26],"some":[27],"problem":[28],"domains,":[29],"however,":[30],"alternative":[31],"may":[34],"allow":[35],"learn":[38],"more":[39,42],"quickly":[40],"or":[41],"effectively.":[43],"Here":[44],"we":[45],"describe":[46],"work":[47],"on":[48],"use":[50],"genetic":[52],"programming":[53],"find":[55],"novel":[56],"improve":[60],"system":[62],"performance.":[63],"We":[64],"briefly":[65],"present":[66],"core":[68],"concepts":[69],"our":[71,73,102],"approach,":[72],"motivations":[74],"in":[75,101],"developing":[76],"it,":[77],"and":[78,99],"reasons":[79],"believe":[81],"approach":[84],"has":[85],"promise":[86],"for":[87],"production":[89],"highly":[91],"successful":[92],"adaptive":[93],"technologies.":[94],"Experimental":[95],"results":[96],"presented":[98],"analyzed":[100],"full":[103],"report":[104],"[3].":[105]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}