{"id":"https://openalex.org/W1974126445","doi":"https://doi.org/10.1109/siu.2013.6531546","title":"Implementation of Reinforcement Learning by transfering sub-goal policies in robot navigation","display_name":"Implementation of Reinforcement Learning by transfering sub-goal policies in robot navigation","publication_year":2013,"publication_date":"2013-04-01","ids":{"openalex":"https://openalex.org/W1974126445","doi":"https://doi.org/10.1109/siu.2013.6531546","mag":"1974126445"},"language":"en","primary_location":{"id":"doi:10.1109/siu.2013.6531546","is_oa":false,"landing_page_url":"https://doi.org/10.1109/siu.2013.6531546","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 21st Signal Processing and Communications Applications Conference (SIU)","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/A5070919769","display_name":"Bar\u0131\u015f G\u00f6k\u00e7e","orcid":"https://orcid.org/0000-0001-6141-7625"},"institutions":[{"id":"https://openalex.org/I4405392","display_name":"Bo\u011fazi\u00e7i University","ror":"https://ror.org/03z9tma90","country_code":"TR","type":"education","lineage":["https://openalex.org/I4405392"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"B. Gokce","raw_affiliation_strings":["Bilgisayar M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc, Bo\u011fazi\u00e7i \u00dcniversitesi, Istanbul, Turkey","Bilgisayar Muhendisligi Bolumu, Bogazici Univ., Istanbul, Turkey"],"affiliations":[{"raw_affiliation_string":"Bilgisayar M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc, Bo\u011fazi\u00e7i \u00dcniversitesi, Istanbul, Turkey","institution_ids":["https://openalex.org/I4405392"]},{"raw_affiliation_string":"Bilgisayar Muhendisligi Bolumu, Bogazici Univ., Istanbul, Turkey","institution_ids":["https://openalex.org/I4405392"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042178241","display_name":"H. Levent Ak\u0131n","orcid":"https://orcid.org/0000-0003-0439-8805"},"institutions":[{"id":"https://openalex.org/I4405392","display_name":"Bo\u011fazi\u00e7i University","ror":"https://ror.org/03z9tma90","country_code":"TR","type":"education","lineage":["https://openalex.org/I4405392"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"H. L. Akin","raw_affiliation_strings":["Bilgisayar Muhendisligi Bolumu, Bogazici Univ., Istanbul, Turkey"],"affiliations":[{"raw_affiliation_string":"Bilgisayar Muhendisligi Bolumu, Bogazici Univ., Istanbul, Turkey","institution_ids":["https://openalex.org/I4405392"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5070919769"],"corresponding_institution_ids":["https://openalex.org/I4405392"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.05690431,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"8","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/T12288","display_name":"Optimization and Search Problems","score":0.9926999807357788,"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"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9872000217437744,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8151940107345581},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.759976863861084},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.7387391924858093},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.6311397552490234},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6239098310470581},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5527797341346741},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.5381063222885132},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.5288451910018921},{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.49925971031188965},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48883241415023804},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44448941946029663},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4343312382698059},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4189996123313904},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3705901503562927},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.2850121259689331},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08423066139221191}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8151940107345581},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.759976863861084},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.7387391924858093},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.6311397552490234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6239098310470581},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5527797341346741},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.5381063222885132},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.5288451910018921},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.49925971031188965},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48883241415023804},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44448941946029663},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4343312382698059},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4189996123313904},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3705901503562927},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.2850121259689331},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08423066139221191},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","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},{"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/siu.2013.6531546","is_oa":false,"landing_page_url":"https://doi.org/10.1109/siu.2013.6531546","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 21st Signal Processing and Communications Applications Conference (SIU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W60146956","https://openalex.org/W1536990779","https://openalex.org/W1544120923","https://openalex.org/W1586944634","https://openalex.org/W1598052524","https://openalex.org/W1608267696","https://openalex.org/W1647196294","https://openalex.org/W1968768508","https://openalex.org/W1980452903","https://openalex.org/W2041141995","https://openalex.org/W2090170171","https://openalex.org/W2124695578","https://openalex.org/W2133040789","https://openalex.org/W2143435603","https://openalex.org/W2156493855","https://openalex.org/W2164114810","https://openalex.org/W2326783255","https://openalex.org/W6602475252","https://openalex.org/W6632315374","https://openalex.org/W6635131279","https://openalex.org/W6635923701","https://openalex.org/W6679818365","https://openalex.org/W6680976742","https://openalex.org/W6682768811"],"related_works":["https://openalex.org/W1976483367","https://openalex.org/W1812381063","https://openalex.org/W2373034895","https://openalex.org/W2171128163","https://openalex.org/W2171968955","https://openalex.org/W155730701","https://openalex.org/W2360485332","https://openalex.org/W2542410050","https://openalex.org/W2352079541","https://openalex.org/W2418726961"],"abstract_inverted_index":{"Although":[0],"Reinforcement":[1],"Learning":[2],"(RL)":[3],"is":[4,124,154,172],"one":[5],"of":[6,17,25,33,53,56,69,74,95,114,121,130,138,145,151],"the":[7,15,20,26,30,34,40,43,51,54,57,63,67,70,77,83,88,92,103,111,115,127,131,135,139,163],"most":[8],"popular":[9],"learning":[10,31,93,99,128],"methods,":[11],"it":[12],"suffers":[13],"from":[14,100],"curse":[16,55],"dimensionality.":[18],"If":[19],"state":[21],"and":[22,38],"action":[23],"domains":[24],"problem":[27,78],"are":[28],"immense,":[29],"rate":[32,129],"agent":[35,41,112,132],"decreases":[36],"dramatically":[37],"eventually":[39],"loses":[42],"ability":[44],"to":[45,49,86,125,155,160],"learn.":[46],"In":[47],"order":[48],"eliminate":[50],"effects":[52],"dimensionality,":[58],"researchers":[59],"typically":[60],"concentrate":[61],"on":[62,174],"methods":[64],"that":[65],"reduce":[66],"complexity":[68],"problems.":[71],"While":[72,98],"some":[73],"them":[75],"model":[76],"in":[79,166,179],"a":[80,143,167,175,180],"hierarchical":[81],"manner,":[82],"others":[84],"try":[85],"transfer":[87,161],"knowledge":[89,108,140,165],"obtained":[90],"during":[91],"process":[94],"simpler":[96],"tasks.":[97],"scratch":[101],"ignores":[102],"previous":[104,146],"experiences,":[105],"transferring":[106,134],"full":[107],"may":[109],"mislead":[110],"because":[113],"conflicting":[116],"requirements.":[117],"The":[118,148,169],"main":[119,149],"goal":[120],"this":[122,152],"study":[123,153],"improve":[126],"by":[133],"relevant":[136,164],"parts":[137],"acquired":[141],"as":[142],"result":[144],"experiences.":[147],"contribution":[150],"merge":[156],"these":[157],"two":[158],"approaches":[159],"only":[162],"setting.":[168],"proposed":[170],"method":[171],"tested":[173],"robot":[176],"navigation":[177],"task":[178],"simulated":[181],"roombased":[182],"environment.":[183]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}