{"id":"https://openalex.org/W2164954644","doi":"https://doi.org/10.1109/riiss.2011.5945778","title":"A study on Reinforcement Learning system for agents to acquire cooperative behavior in gap-widening situations","display_name":"A study on Reinforcement Learning system for agents to acquire cooperative behavior in gap-widening situations","publication_year":2011,"publication_date":"2011-04-01","ids":{"openalex":"https://openalex.org/W2164954644","doi":"https://doi.org/10.1109/riiss.2011.5945778","mag":"2164954644"},"language":"en","primary_location":{"id":"doi:10.1109/riiss.2011.5945778","is_oa":false,"landing_page_url":"https://doi.org/10.1109/riiss.2011.5945778","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Workshop on Robotic Intelligence In Informationally Structured Space","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/A5023284745","display_name":"Daisuke Kitakoshi","orcid":"https://orcid.org/0000-0002-2351-8334"},"institutions":[{"id":"https://openalex.org/I4210086624","display_name":"National Institute of Technology, Tokyo College","ror":"https://ror.org/002k06d85","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210086624","https://openalex.org/I4210120810"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daisuke Kitakoshi","raw_affiliation_strings":["Department of Computer Science, Tokyo National College of Technology, Hachioji, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tokyo National College of Technology, Hachioji, Tokyo, Japan","institution_ids":["https://openalex.org/I4210086624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071324689","display_name":"Ryunosuke Miyauchi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ryunosuke Miyauchi","raw_affiliation_strings":["Nextware Limited, Minato, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nextware Limited, Minato, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045456960","display_name":"Masato Suzuki","orcid":"https://orcid.org/0000-0003-2040-3029"},"institutions":[{"id":"https://openalex.org/I4210086624","display_name":"National Institute of Technology, Tokyo College","ror":"https://ror.org/002k06d85","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210086624","https://openalex.org/I4210120810"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Suzuki","raw_affiliation_strings":["Department of Computer Science, Tokyo National College of Technology, Hachioji, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tokyo National College of Technology, Hachioji, Tokyo, Japan","institution_ids":["https://openalex.org/I4210086624"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1455344,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"43","issue":null,"first_page":"55","last_page":"62"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9941999912261963,"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":0.9941999912261963,"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":0.9379000067710876,"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":0.7364972233772278},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6091924905776978},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5398096442222595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41871339082717896},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37770724296569824},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.22550824284553528},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.08968937397003174}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7364972233772278},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6091924905776978},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5398096442222595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41871339082717896},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37770724296569824},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.22550824284553528},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.08968937397003174}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/riiss.2011.5945778","is_oa":false,"landing_page_url":"https://doi.org/10.1109/riiss.2011.5945778","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Workshop on Robotic Intelligence In Informationally Structured Space","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":10,"referenced_works":["https://openalex.org/W1979052604","https://openalex.org/W1995663008","https://openalex.org/W2032854309","https://openalex.org/W2034558718","https://openalex.org/W2048889687","https://openalex.org/W2091328279","https://openalex.org/W2128421316","https://openalex.org/W2239734259","https://openalex.org/W6679078946","https://openalex.org/W6689919066"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588"],"abstract_inverted_index":{"This":[0],"article":[1],"proposes":[2],"an":[3],"Interactive":[4],"Hierarchical":[5],"Reinforcement":[6],"Learning":[7],"system":[8],"(IH-RL).":[9],"The":[10,70],"goal":[11],"of":[12,37,67],"our":[13,68],"study":[14],"is":[15],"that":[16,73],"the":[17,20,64,74],"agents":[18],"using":[19],"IH-RL":[21,75],"acquire":[22],"adequate":[23],"behaviors":[24],"to":[25,55,62],"cooperative":[26,81],"in":[27,34,48],"\u201cgap-widening\u201d":[28],"situations.":[29],"Such":[30],"situations":[31,78],"are":[32,52,59],"observed":[33],"a":[35,49],"variety":[36],"real-world":[38],"environments":[39],"(e.g.,":[40],"economic":[41],"gaps":[42],"between":[43,46],"humans":[44],"or":[45],"companies":[47],"community),":[50],"and":[51],"thus":[53],"important":[54],"solve.":[56],"Computer":[57],"simulations":[58],"carried":[60],"out":[61],"evaluate":[63],"basic":[65],"performance":[66],"system.":[69],"results":[71],"showed":[72],"resolves":[76],"gap-widening":[77],"through":[79],"agents'":[80],"behaviors.":[82]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}