{"id":"https://openalex.org/W1964755999","doi":"https://doi.org/10.1145/1655925.1656047","title":"A reward field model generation in Q-learning by dynamic programming","display_name":"A reward field model generation in Q-learning by dynamic programming","publication_year":2009,"publication_date":"2009-11-24","ids":{"openalex":"https://openalex.org/W1964755999","doi":"https://doi.org/10.1145/1655925.1656047","mag":"1964755999"},"language":"en","primary_location":{"id":"doi:10.1145/1655925.1656047","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1655925.1656047","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Conference on Interaction Sciences: Information Technology, Culture and Human","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/A5076237464","display_name":"Yunsick Sung","orcid":"https://orcid.org/0000-0003-3732-5346"},"institutions":[{"id":"https://openalex.org/I205490536","display_name":"Dongguk University","ror":"https://ror.org/057q6n778","country_code":"KR","type":"education","lineage":["https://openalex.org/I205490536"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Yunsick Sung","raw_affiliation_strings":["Dongguk University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Dongguk University, Seoul, Korea","institution_ids":["https://openalex.org/I205490536"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067433402","display_name":"Kyungeun Cho","orcid":"https://orcid.org/0000-0003-2219-0848"},"institutions":[{"id":"https://openalex.org/I205490536","display_name":"Dongguk University","ror":"https://ror.org/057q6n778","country_code":"KR","type":"education","lineage":["https://openalex.org/I205490536"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyungeun Cho","raw_affiliation_strings":["Dongguk University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Dongguk University, Seoul, Korea","institution_ids":["https://openalex.org/I205490536"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066865239","display_name":"Kyhyun Um","orcid":"https://orcid.org/0000-0003-2623-9506"},"institutions":[{"id":"https://openalex.org/I205490536","display_name":"Dongguk University","ror":"https://ror.org/057q6n778","country_code":"KR","type":"education","lineage":["https://openalex.org/I205490536"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyhyun Um","raw_affiliation_strings":["Dongguk University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Dongguk University, Seoul, Korea","institution_ids":["https://openalex.org/I205490536"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5076237464"],"corresponding_institution_ids":["https://openalex.org/I205490536"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06691009,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"674","last_page":"679"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9987999796867371,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9805999994277954,"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/computer-science","display_name":"Computer science","score":0.7579874992370605},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6848183870315552},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.6525921821594238},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6456559300422668},{"id":"https://openalex.org/keywords/notice","display_name":"Notice","score":0.6215678453445435},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6172573566436768},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.611082136631012},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5300027132034302},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.4820912182331085},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47127315402030945},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.4440820813179016},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.4312566816806793},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0941939651966095},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08247694373130798}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7579874992370605},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6848183870315552},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.6525921821594238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6456559300422668},{"id":"https://openalex.org/C2779913896","wikidata":"https://www.wikidata.org/wiki/Q7063001","display_name":"Notice","level":2,"score":0.6215678453445435},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6172573566436768},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.611082136631012},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5300027132034302},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.4820912182331085},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47127315402030945},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.4440820813179016},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.4312566816806793},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0941939651966095},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08247694373130798},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1655925.1656047","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1655925.1656047","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Conference on Interaction Sciences: Information Technology, Culture and Human","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1515851193","https://openalex.org/W1680254737","https://openalex.org/W1927790226","https://openalex.org/W2095779990","https://openalex.org/W2103120971","https://openalex.org/W2104308387","https://openalex.org/W2113913482","https://openalex.org/W2117629901","https://openalex.org/W2132602063","https://openalex.org/W2808421695","https://openalex.org/W2952458761","https://openalex.org/W3145128584"],"related_works":["https://openalex.org/W2742483371","https://openalex.org/W2341346307","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W2357975469","https://openalex.org/W4400868993","https://openalex.org/W2145363145","https://openalex.org/W2152445738","https://openalex.org/W3148138296","https://openalex.org/W4388937744"],"abstract_inverted_index":{"Many":[0],"obstacles":[1],"and":[2,9,94,125,205],"paths":[3],"exist":[4],"in":[5,25],"a":[6,43,49,62,82,88,115,136,141,167,183],"real":[7],"environment,":[8],"hence,":[10],"it":[11,29,46,79,85,157,164,180,186],"is":[12,23,64,102,117,158,171],"difficult":[13],"for":[14,51],"an":[15,20,38,53,71,75,99,108,150],"agent":[16,39,72,109,151,170],"to":[17,41,60,81,97,106,110,154,160,176],"learn":[18,111],"such":[19,26,140],"environment.":[21],"Q-learning":[22,204],"suitable":[24],"cases":[27],"because":[28],"does":[30],"not":[31],"define":[32],"any":[33],"learning":[34,69,92,95],"model.":[35],"By":[36,193],"Q-learning,":[37,113],"learns":[40],"reach":[42],"state":[44,83,162,178],"wherein":[45,84,163,179],"can":[47,127,165,181],"receive":[48,61,87,166,182],"reward":[50,63,184,191],"selecting":[52],"action.":[54],"However,":[55],"no":[56],"information":[57],"on":[58],"how":[59],"available.":[65],"In":[66,104,131],"the":[67,91,121,161,174,177,188,199,206,213,217],"initial":[68],"stage,":[70],"sometimes":[73],"selects":[74],"action":[76,101],"that":[77,138,212,225],"makes":[78],"move":[80],"cannot":[86],"reward.":[89,168],"Hence,":[90],"time":[93,124],"cost":[96,126],"select":[98],"optimal":[100],"increased.":[103],"order":[105],"assist":[107],"by":[112,144,173],"if":[114],"model":[116,142,148,175],"created":[118],"automatically,":[119],"both":[120],"problems":[122],"of":[123,190,216,226],"be":[128,152],"solved":[129],"together.":[130],"this":[132],"paper,":[133],"we":[134,196],"propose":[135],"method":[137,219],"creates":[139],"automatically":[143],"dynamic":[145],"programming.":[146],"This":[147],"causes":[149],"able":[153],"notice":[155],"when":[156,185],"close":[159],"An":[169],"driven":[172],"enters":[187],"field":[189],"affection.":[192],"conducting":[194],"experiments,":[195],"also":[197],"compared":[198],"success":[200,214],"rate":[201,215],"between":[202],"conventional":[203],"proposed":[207,218],"method.":[208],"Our":[209],"results":[210],"showed":[211],"was":[220],"approximately":[221],"187%":[222],"higher":[223],"than":[224],"Q-learning.":[227]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}