{"id":"https://openalex.org/W3098951764","doi":"https://doi.org/10.1109/case48305.2020.9249227","title":"Reinforcement Learning with Converging Goal Space and Binary Reward Function","display_name":"Reinforcement Learning with Converging Goal Space and Binary Reward Function","publication_year":2020,"publication_date":"2020-08-01","ids":{"openalex":"https://openalex.org/W3098951764","doi":"https://doi.org/10.1109/case48305.2020.9249227","mag":"3098951764"},"language":"en","primary_location":{"id":"doi:10.1109/case48305.2020.9249227","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case48305.2020.9249227","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5113922239","display_name":"Wooseok Ro","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wooseok Ro","raw_affiliation_strings":["Yonsei University, Seodaemun-gu, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei University, Seodaemun-gu, Seoul, Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085333080","display_name":"Wonseok Jeon","orcid":"https://orcid.org/0000-0003-2917-8577"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wonseok Jeon","raw_affiliation_strings":["Yonsei University, Seodaemun-gu, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei University, Seodaemun-gu, Seoul, Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073581279","display_name":"Hamid Bamshad","orcid":"https://orcid.org/0000-0002-1248-8803"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hamid Bamshad","raw_affiliation_strings":["Yonsei University, Seodaemun-gu, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei University, Seodaemun-gu, Seoul, Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045165772","display_name":"Hyunseok Yang","orcid":"https://orcid.org/0000-0002-1872-7449"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunseok Yang","raw_affiliation_strings":["Yonsei University, Seodaemun-gu, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei University, Seodaemun-gu, Seoul, Korea","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I193775966"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"921","last_page":"927"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9886999726295471,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9869999885559082,"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":0.7844276428222656},{"id":"https://openalex.org/keywords/hindsight-bias","display_name":"Hindsight bias","score":0.7391687631607056},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6961522102355957},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6549181938171387},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5675600171089172},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.561694324016571},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5537835955619812},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47782090306282043},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.47781044244766235},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4659351706504822},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11490687727928162},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.07921692728996277}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7844276428222656},{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.7391687631607056},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6961522102355957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6549181938171387},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5675600171089172},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.561694324016571},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5537835955619812},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47782090306282043},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.47781044244766235},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4659351706504822},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11490687727928162},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.07921692728996277},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/case48305.2020.9249227","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case48305.2020.9249227","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6198494521","display_name":null,"funder_award_id":"NRF-2018R1D1A1B07049267","funder_id":"https://openalex.org/F4320335891","funder_display_name":"Science and Technology Development Center, Ministry of Education"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320335891","display_name":"Science and Technology Development Center, Ministry of Education","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W24477102","https://openalex.org/W567721252","https://openalex.org/W1499408472","https://openalex.org/W1515851193","https://openalex.org/W1522301498","https://openalex.org/W1594783240","https://openalex.org/W1757796397","https://openalex.org/W1769460679","https://openalex.org/W1777239053","https://openalex.org/W1977655452","https://openalex.org/W1996847178","https://openalex.org/W2051620263","https://openalex.org/W2071311198","https://openalex.org/W2079247031","https://openalex.org/W2139160917","https://openalex.org/W2158782408","https://openalex.org/W2173248099","https://openalex.org/W2257979135","https://openalex.org/W2575705757","https://openalex.org/W2737215407","https://openalex.org/W2789008106","https://openalex.org/W2890965997","https://openalex.org/W2963099939","https://openalex.org/W2963311874","https://openalex.org/W2963411833","https://openalex.org/W2963864421","https://openalex.org/W2964001908","https://openalex.org/W2964121744","https://openalex.org/W3010498949","https://openalex.org/W3037207827","https://openalex.org/W3101442004","https://openalex.org/W4246515624","https://openalex.org/W4293872189","https://openalex.org/W4298857966","https://openalex.org/W4300799055","https://openalex.org/W6600984476","https://openalex.org/W6616173779","https://openalex.org/W6635508374","https://openalex.org/W6637770816","https://openalex.org/W6638088447","https://openalex.org/W6680185541","https://openalex.org/W6740801417","https://openalex.org/W6966558720"],"related_works":["https://openalex.org/W3197854638","https://openalex.org/W3140454661","https://openalex.org/W4245029315","https://openalex.org/W1492315459","https://openalex.org/W1512434910","https://openalex.org/W2540910169","https://openalex.org/W3148904318","https://openalex.org/W2139970489","https://openalex.org/W2022803902","https://openalex.org/W2105474389"],"abstract_inverted_index":{"Usage":[0],"of":[1,10,41,80,140,184,196],"a":[2,70,89,113,122,132,178,201],"sparse":[3,202],"and":[4,66,96,106,171,188,203,222],"binary":[5,114,204],"reward":[6,129,163,205,212],"function":[7,130,164,213,227],"remains":[8],"one":[9],"the":[11,21,39,43,63,78,81,128,138,143,150,154,158,182,185,191,210,226],"most":[12],"challenging":[13],"problems":[14,59],"in":[15,108,120,157,216],"reinforcement":[16],"learning.":[17,136],"In":[18,84],"particular,":[19],"when":[20,69],"environments":[22,110,218],"wherein":[23],"robotic":[24,186,233],"agents":[25,102],"learn":[26,36,103],"are":[27],"sufficiently":[28],"vast,":[29],"it":[30],"is":[31,45,146,228],"much":[32],"more":[33,133],"difficult":[34],"to":[35,54,149,153,165,194,230],"tasks":[37,104],"because":[38],"probability":[40],"reaching":[42],"goal":[44,124,144],"minimal.":[46],"A":[47],"Hindsight":[48],"Experience":[49],"Replay":[50],"algorithm":[51],"was":[52],"proposed":[53,211],"overcome":[55],"these":[56],"difficulties;":[57],"however,":[58],"persist":[60],"that":[61,195,198,209,225],"affect":[62],"learning":[64,68,71,82,192],"speed":[65],"delay":[67],"agent":[72],"cannot":[73],"receive":[74],"proper":[75],"rewards":[76],"at":[77,177],"beginning":[79],"process.":[83],"this":[85,162],"paper,":[86],"we":[87,223],"present":[88],"simple":[90],"method":[91],"called":[92],"Converging":[93],"Goal":[94],"Space":[95],"Binary":[97],"Reward":[98],"Function,":[99],"which":[100,173],"helps":[101],"easily":[105],"efficiently":[107],"large":[109,217],"while":[111],"providing":[112],"reward.":[115],"At":[116],"an":[117],"early":[118],"stage":[119],"training,":[121],"larger":[123],"space":[125,145],"margin":[126],"facilitates":[127],"for":[131],"rapid":[134],"policy":[135],"As":[137],"number":[139],"successes":[141],"increases,":[142],"gradually":[147],"reduced":[148],"size":[151,155],"used":[152,156],"test.":[159],"We":[160,207],"apply":[161],"two":[166],"different":[167],"task":[168],"experiments:":[169],"sliding":[170],"throwing,":[172],"must":[174],"be":[175],"explored":[176],"wider":[179],"range":[180],"than":[181],"reach":[183],"arms,":[187],"then":[189],"compare":[190],"efficiency":[193],"experiments":[197],"only":[199],"employ":[200],"function.":[206],"show":[208],"performs":[214],"better":[215],"using":[219],"physics":[220],"simulation,":[221],"demonstrate":[224],"applicable":[229],"real":[231],"world":[232],"arms.":[234]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}