{"id":"https://openalex.org/W2409924634","doi":"https://doi.org/10.1109/iccsce.2015.7482161","title":"Simplified online Q-learning for LEGO EV3 robot","display_name":"Simplified online Q-learning for LEGO EV3 robot","publication_year":2015,"publication_date":"2015-11-01","ids":{"openalex":"https://openalex.org/W2409924634","doi":"https://doi.org/10.1109/iccsce.2015.7482161","mag":"2409924634"},"language":"en","primary_location":{"id":"doi:10.1109/iccsce.2015.7482161","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccsce.2015.7482161","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Control System, Computing and Engineering (ICCSCE)","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/A5101662026","display_name":"Ke Xu","orcid":"https://orcid.org/0000-0002-6241-8352"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ke Xu","raw_affiliation_strings":["Science and Technology on Integrated Information System Laboratory Institute of Software, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Science and Technology on Integrated Information System Laboratory Institute of Software, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030271803","display_name":"Fengge Wu","orcid":"https://orcid.org/0000-0002-1958-8321"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengge Wu","raw_affiliation_strings":["Science and Technology on Integrated Information System Laboratory Institute of Software, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Science and Technology on Integrated Information System Laboratory Institute of Software, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069584904","display_name":"Junsuo Zhao","orcid":"https://orcid.org/0000-0001-8950-4157"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junsuo Zhao","raw_affiliation_strings":["Science and Technology on Integrated Information System Laboratory Institute of Software, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Science and Technology on Integrated Information System Laboratory Institute of Software, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101662026"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210128818"],"apc_list":null,"apc_paid":null,"fwci":0.4314,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.79092778,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"77","last_page":"80"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9991999864578247,"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/T12288","display_name":"Optimization and Search Problems","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.7880222797393799},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.7641888856887817},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7625744342803955},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6993885636329651},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5544431209564209},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5510976910591125},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.5197879076004028},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4997735023498535},{"id":"https://openalex.org/keywords/lookup-table","display_name":"Lookup table","score":0.4628668427467346},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4623049795627594},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4236617684364319},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3270608186721802},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.26416313648223877},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.22146379947662354},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1876751184463501},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08791530132293701}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7880222797393799},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.7641888856887817},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7625744342803955},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6993885636329651},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5544431209564209},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5510976910591125},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.5197879076004028},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4997735023498535},{"id":"https://openalex.org/C134835016","wikidata":"https://www.wikidata.org/wiki/Q690265","display_name":"Lookup table","level":2,"score":0.4628668427467346},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4623049795627594},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4236617684364319},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3270608186721802},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26416313648223877},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.22146379947662354},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1876751184463501},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08791530132293701},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccsce.2015.7482161","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccsce.2015.7482161","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Control System, Computing and Engineering (ICCSCE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5199999809265137}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1564424139","https://openalex.org/W2075268401","https://openalex.org/W2101286551","https://openalex.org/W2122410182","https://openalex.org/W2993885703","https://openalex.org/W6771792483"],"related_works":["https://openalex.org/W2742483371","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W4376605461","https://openalex.org/W4400868993","https://openalex.org/W2361647908","https://openalex.org/W3127551068"],"abstract_inverted_index":{"Q-learning":[0,30,41,81],"is":[1,10,24,37],"a":[2,46,88],"kind":[3],"of":[4,59],"model-free":[5],"reinforcement":[6],"learning":[7],"algorithm":[8,74],"which":[9],"effective":[11],"in":[12,64,91],"Robot's":[13],"navigation":[14,92],"applications.":[15],"Unfortunately,":[16],"Lego":[17],"Mindstorms":[18],"EV3":[19],"robot's":[20],"file":[21],"writing":[22],"speed":[23],"sometimes":[25],"too":[26],"slow":[27],"to":[28,39,86],"implement":[29],"algorithm.":[31],"In":[32],"this":[33],"paper,":[34],"an":[35],"approach":[36],"proposed":[38],"simplify":[40],"discrete":[42],"value":[43],"table":[44],"into":[45],"new":[47],"version":[48],"that":[49,72],"stores":[50],"only":[51],"one":[52],"optimum":[53],"action":[54],"and":[55,68],"its":[56],"Q-value":[57,63],"instead":[58],"storing":[60],"every":[61],"action's":[62],"each":[65],"state.":[66],"Exploration":[67],"contrast":[69],"experiments":[70],"show":[71],"our":[73],"learns":[75],"much":[76],"faster":[77],"than":[78],"the":[79,84],"original":[80],"without":[82],"losing":[83],"ability":[85],"find":[87],"better":[89],"policy":[90],"task.":[93]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}