{"id":"https://openalex.org/W2999580272","doi":"https://doi.org/10.1109/icmlc48188.2019.8949181","title":"Behavior Acquisition on a Mobile Robot Using Reinforcement Learning With Continuous State Space","display_name":"Behavior Acquisition on a Mobile Robot Using Reinforcement Learning With Continuous State Space","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2999580272","doi":"https://doi.org/10.1109/icmlc48188.2019.8949181","mag":"2999580272"},"language":"en","primary_location":{"id":"doi:10.1109/icmlc48188.2019.8949181","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmlc48188.2019.8949181","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Machine Learning and Cybernetics (ICMLC)","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/A5026646725","display_name":"Tomoyuki Arai","orcid":"https://orcid.org/0000-0001-5138-601X"},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Tomoyuki Arai","raw_affiliation_strings":["Graduate school of Systems Design, Tokyo Metropolitan University,Tokyo,Japan","Graduate school of Systems Design, Tokyo Metropolitan University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate school of Systems Design, Tokyo Metropolitan University,Tokyo,Japan","institution_ids":["https://openalex.org/I69740276"]},{"raw_affiliation_string":"Graduate school of Systems Design, Tokyo Metropolitan University, Tokyo, Japan","institution_ids":["https://openalex.org/I69740276"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087750601","display_name":"Yuichiro Toda","orcid":"https://orcid.org/0000-0003-4170-2300"},"institutions":[{"id":"https://openalex.org/I136446963","display_name":"Okayama University of Science","ror":"https://ror.org/05aevyc10","country_code":"JP","type":"education","lineage":["https://openalex.org/I136446963"]},{"id":"https://openalex.org/I163770644","display_name":"Okayama University","ror":"https://ror.org/02pc6pc55","country_code":"JP","type":"education","lineage":["https://openalex.org/I163770644"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuichiro Toda","raw_affiliation_strings":["Graduate school of Natural Science of Technology, Okayama University,Okayama,Japan","Graduate school of Natural Science of Technology, Okayama University, Okayama, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate school of Natural Science of Technology, Okayama University,Okayama,Japan","institution_ids":["https://openalex.org/I136446963","https://openalex.org/I163770644"]},{"raw_affiliation_string":"Graduate school of Natural Science of Technology, Okayama University, Okayama, Japan","institution_ids":["https://openalex.org/I163770644"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074076109","display_name":"Naoyuki Kubota","orcid":"https://orcid.org/0000-0001-8829-037X"},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoyuki Kubota","raw_affiliation_strings":["Graduate school of Systems Design, Tokyo Metropolitan University,Tokyo,Japan","Graduate school of Systems Design, Tokyo Metropolitan University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate school of Systems Design, Tokyo Metropolitan University,Tokyo,Japan","institution_ids":["https://openalex.org/I69740276"]},{"raw_affiliation_string":"Graduate school of Systems Design, Tokyo Metropolitan University, Tokyo, Japan","institution_ids":["https://openalex.org/I69740276"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5026646725"],"corresponding_institution_ids":["https://openalex.org/I69740276"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17966818,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9919999837875366,"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/T10320","display_name":"Neural Networks and Applications","score":0.9840999841690063,"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":0.9414235353469849},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.7417874932289124},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6863890886306763},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.6539878249168396},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.6238034963607788},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5865179896354675},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5725703835487366},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5418842434883118},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5228177309036255},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.4163374900817871},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1915993094444275},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09421253204345703},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08135387301445007}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9414235353469849},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.7417874932289124},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6863890886306763},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.6539878249168396},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.6238034963607788},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5865179896354675},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5725703835487366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5418842434883118},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5228177309036255},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.4163374900817871},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1915993094444275},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09421253204345703},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08135387301445007},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmlc48188.2019.8949181","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmlc48188.2019.8949181","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Machine Learning and Cybernetics (ICMLC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.7200000286102295,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1560851313","https://openalex.org/W1991848143","https://openalex.org/W2066235179","https://openalex.org/W2100644648","https://openalex.org/W2113045410","https://openalex.org/W2121863487","https://openalex.org/W2138754805","https://openalex.org/W3036512766","https://openalex.org/W4214717370","https://openalex.org/W6633708292","https://openalex.org/W6667149791","https://openalex.org/W6674885835","https://openalex.org/W6677005534","https://openalex.org/W6680294583"],"related_works":["https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W2126211886","https://openalex.org/W2371091044","https://openalex.org/W2171010636","https://openalex.org/W87513465","https://openalex.org/W1966803121","https://openalex.org/W2391666574"],"abstract_inverted_index":{"In":[0,18,51],"the":[1,9,23,31,42,54,70,77,80,83,97,103],"application":[2],"of":[3,11,33,41,44,79],"Reinforcement":[4,88],"Learning":[5,89],"to":[6,20,28,75,102],"real":[7],"tasks,":[8],"construction":[10,43],"state":[12,45,58,72,98],"space":[13,46,59,73,99],"is":[14],"a":[15,39,57],"significant":[16],"problem.":[17],"order":[19],"use":[21],"in":[22],"real-world":[24],"environment,":[25],"we":[26,37,85],"need":[27],"deal":[29],"with":[30],"problem":[32],"continuous":[34],"information.":[35],"Therefore,":[36],"proposed":[38],"method":[40],"using":[47],"Growing":[48],"Neural":[49],"Gas.":[50],"our":[52],"method,":[53],"agent":[55],"constructs":[56],"model":[60,74,100],"from":[61],"its":[62],"own":[63],"experience":[64],"autonomously.":[65],"Furthermore,":[66],"it":[67],"can":[68],"reconstruct":[69],"suitable":[71],"adapt":[76],"complication":[78],"environment.":[81,104],"Through":[82],"experiments,":[84],"showed":[86],"that":[87],"could":[90],"be":[91],"performed":[92],"efficiently":[93],"by":[94],"successively":[95],"updating":[96],"according":[101]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}