{"id":"https://openalex.org/W1996272383","doi":"https://doi.org/10.1109/mhs.2011.6102214","title":"Evolutionary approach of reward function for reinforcement learning using genetic programming","display_name":"Evolutionary approach of reward function for reinforcement learning using genetic programming","publication_year":2011,"publication_date":"2011-11-01","ids":{"openalex":"https://openalex.org/W1996272383","doi":"https://doi.org/10.1109/mhs.2011.6102214","mag":"1996272383"},"language":"en","primary_location":{"id":"doi:10.1109/mhs.2011.6102214","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mhs.2011.6102214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 International Symposium on Micro-NanoMechatronics and Human Science","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/A5074991925","display_name":"Shota Sumino","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Shota Sumino","raw_affiliation_strings":["Department of Computer Science and Engineering, Nagoya Institute of Technology, Nagoya, Japan","Department of Computer Science and Engineering, Nagoya Institute of Technology, Gokiso-cho Showa-ku 466-8555, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Nagoya Institute of Technology, Gokiso-cho Showa-ku 466-8555, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113702771","display_name":"Atsuko Mutoh","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsuko Mutoh","raw_affiliation_strings":["Department of Computer Science and Engineering, Nagoya Institute of Technology, Nagoya, Japan","Department of Computer Science and Engineering, Nagoya Institute of Technology, Gokiso-cho Showa-ku 466-8555, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Nagoya Institute of Technology, Gokiso-cho Showa-ku 466-8555, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088832778","display_name":"Sh\u014dhei Kato","orcid":"https://orcid.org/0000-0003-4130-2729"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shohei Kato","raw_affiliation_strings":["Department of Computer Science and Engineering, Nagoya Institute of Technology, Nagoya, Japan","Department of Computer Science and Engineering, Nagoya Institute of Technology, Gokiso-cho Showa-ku 466-8555, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Nagoya Institute of Technology, Gokiso-cho Showa-ku 466-8555, Japan","institution_ids":["https://openalex.org/I197274945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5074991925"],"corresponding_institution_ids":["https://openalex.org/I197274945"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.07475376,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9695000052452087,"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":0.9542999863624573,"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":0.8594397902488708},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6827590465545654},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.673724353313446},{"id":"https://openalex.org/keywords/genetic-programming","display_name":"Genetic programming","score":0.6211289167404175},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6148055791854858},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.6092369556427002},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4935241937637329},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47817403078079224},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4175463318824768},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.22324258089065552},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10887143015861511}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8594397902488708},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6827590465545654},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.673724353313446},{"id":"https://openalex.org/C110332635","wikidata":"https://www.wikidata.org/wiki/Q629498","display_name":"Genetic programming","level":2,"score":0.6211289167404175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6148055791854858},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.6092369556427002},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4935241937637329},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47817403078079224},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4175463318824768},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.22324258089065552},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10887143015861511},{"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mhs.2011.6102214","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mhs.2011.6102214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 International Symposium on Micro-NanoMechatronics and Human Science","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1513108299","https://openalex.org/W1640775274","https://openalex.org/W2098356819","https://openalex.org/W2914656440","https://openalex.org/W4301630257"],"related_works":["https://openalex.org/W2280422768","https://openalex.org/W3143197806","https://openalex.org/W4252555497","https://openalex.org/W3121175838","https://openalex.org/W3016293053","https://openalex.org/W2961374456","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698"],"abstract_inverted_index":{"In":[0,49,111,146,160],"recent":[1],"year,":[2],"reinforcement":[3,51,72],"learning,":[4,52,73],"which":[5,103,172],"acquires":[6],"a":[7,55,116,165,170,173,178,191,202,209],"behavior":[8,17,29,57,205],"of":[9,38,71,142,157,169],"robots":[10],"has":[11],"been":[12],"drawing":[13],"attention.":[14],"A":[15,134],"suitable":[16,28,56,61,135,166,192,204],"is":[18,44,88,138],"autonomously":[19],"acquired":[20],"by":[21,30,46,58,125,131,140,212],"using":[22,108],"this":[23,112,147],"system.":[24],"Robots":[25],"learn":[26],"the":[27,35,60,155,161,181,186,196],"iterating":[31],"action":[32],"and":[33,90,128,195],"receiving":[34],"evaluated":[36,42,130],"value":[37,43],"that":[39,185],"action.":[40],"The":[41],"calculated":[45],"reward":[47,62,75,85,106,119,136,144,167,193,198,210],"function.":[48],"general":[50],"we":[53,99,114,149,163,183],"acquire":[54,201],"setting":[59],"function":[63,137,168,199,211],"for":[64],"each":[65],"problem.":[66],"However":[67],"in":[68,177,206],"previous":[69],"research":[70],"most":[74],"functions":[76,122],"are":[77,123,129],"constructed":[78,213],"based":[79,214],"on":[80,96,215],"human's":[81,216],"heuristics.":[82,217],"To":[83],"construct":[84],"functions,":[86,107],"trial-and-error":[87],"needed,":[89],"it":[91],"imposes":[92],"an":[93,101,151],"enormous":[94],"drain":[95],"humans.":[97],"Therefore":[98],"propose":[100],"approach,":[102,113],"automatically":[104],"generate":[105,164,190],"Genetic":[109,126],"Programming.":[110],"create":[115],"method":[117],"evaluating":[118,132],"functions.":[120,145],"Reward":[121],"generated":[124,139,197],"Programming,":[127],"method.":[133,159],"evolution":[141],"these":[143],"paper,":[148],"conducted":[150],"experiment":[152],"to":[153],"confirm":[154,184],"effectiveness":[156],"proposed":[158,187],"experiment,":[162,182],"problem,":[171],"route":[174],"searching":[175],"problem":[176],"tile-world.":[179],"Through":[180],"approach":[188],"can":[189,200],"function,":[194],"more":[203],"comparison":[207],"with":[208]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}