{"id":"https://openalex.org/W2068857652","doi":"https://doi.org/10.1109/grc.2011.6122650","title":"A reinforcement learning method to improve the sweeping efficiency for an agent","display_name":"A reinforcement learning method to improve the sweeping efficiency for an agent","publication_year":2011,"publication_date":"2011-11-01","ids":{"openalex":"https://openalex.org/W2068857652","doi":"https://doi.org/10.1109/grc.2011.6122650","mag":"2068857652"},"language":"en","primary_location":{"id":"doi:10.1109/grc.2011.6122650","is_oa":false,"landing_page_url":"https://doi.org/10.1109/grc.2011.6122650","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Granular Computing","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/A5023178570","display_name":"Naoto Ohsaka","orcid":"https://orcid.org/0000-0001-9584-4764"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoto Ohsaka","raw_affiliation_strings":["Department of Computer Science, The University of Electro-Communications, Chofu, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Electro-Communications, Chofu, Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"middle","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, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tokyo National College of Technology, Hachioji, Japan","institution_ids":["https://openalex.org/I4210086624"]}]},{"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, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tokyo National College of Technology, Hachioji, 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":0.12941274,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"515","last_page":"520"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9955999851226807,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8382313847541809},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.8139781951904297},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7237388491630554},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.6638541221618652},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.6250403523445129},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.47729718685150146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43515199422836304},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3403913974761963},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.33994317054748535},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14838671684265137},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14689090847969055}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8382313847541809},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.8139781951904297},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7237388491630554},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.6638541221618652},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.6250403523445129},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.47729718685150146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43515199422836304},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3403913974761963},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.33994317054748535},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14838671684265137},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14689090847969055},{"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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/grc.2011.6122650","is_oa":false,"landing_page_url":"https://doi.org/10.1109/grc.2011.6122650","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Granular Computing","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":12,"referenced_works":["https://openalex.org/W140238390","https://openalex.org/W1586494901","https://openalex.org/W1590932131","https://openalex.org/W1604935688","https://openalex.org/W1702514015","https://openalex.org/W1873425142","https://openalex.org/W2052117683","https://openalex.org/W2119520055","https://openalex.org/W2140683500","https://openalex.org/W4247421201","https://openalex.org/W4253365321","https://openalex.org/W6605705772"],"related_works":["https://openalex.org/W2280422768","https://openalex.org/W3143197806","https://openalex.org/W2920061524","https://openalex.org/W4252555497","https://openalex.org/W4310083477","https://openalex.org/W3121175838","https://openalex.org/W3016293053","https://openalex.org/W1690653314","https://openalex.org/W1977959518","https://openalex.org/W2038908348"],"abstract_inverted_index":{"This":[0],"article":[1],"proposes":[2],"a":[3,26,31,46],"reinforcement":[4],"learning":[5],"method":[6],"aimed":[7],"at":[8],"improving":[9],"the":[10,17,36,41,51,70,78,83],"sweeping":[11],"efficiency":[12],"of":[13,33,50,69],"an":[14,20,87],"agent.":[15],"In":[16],"proposed":[18,71],"method,":[19],"agent":[21,37,52,79,88],"attempts":[22],"to":[23,38,63,86],"avoid":[24],"overlapping":[25],"swept":[27],"field":[28,47,84],"by":[29],"using":[30],"combination":[32],"distances":[34],"from":[35],"obstacles":[39],"and":[40,67],"information":[42],"which":[43],"expresses":[44],"whether":[45],"in":[48,82],"front":[49],"has":[53],"already":[54],"been":[55],"swept.":[56],"We":[57],"carried":[58],"out":[59],"several":[60],"computer":[61],"simulations":[62],"evaluate":[64],"basic":[65],"characteristics":[66],"performance":[68],"method.":[72],"The":[73],"empirical":[74],"results":[75],"showed":[76],"that":[77],"behaves":[80],"effectively":[81],"compared":[85],"with":[89],"fixed":[90],"heuristics.":[91]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}