{"id":"https://openalex.org/W4321021831","doi":"https://doi.org/10.1109/access.2023.3246267","title":"Learning Potential in Subgoal-Based Reward Shaping","display_name":"Learning Potential in Subgoal-Based Reward Shaping","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4321021831","doi":"https://doi.org/10.1109/access.2023.3246267"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3246267","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3246267","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10047888.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10047888.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057299724","display_name":"Takato Okudo","orcid":"https://orcid.org/0000-0002-7218-7842"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takato Okudo","raw_affiliation_strings":["Department of Informatics, The Graduate University for Advanced Studies (SOKENDAI), Tokyo, Japan","National Institute of Informatics, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, The Graduate University for Advanced Studies (SOKENDAI), Tokyo, Japan","institution_ids":["https://openalex.org/I200475212"]},{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101954161","display_name":"Seiji Yamada","orcid":"https://orcid.org/0000-0002-5907-7382"},"institutions":[{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]},{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Seiji Yamada","raw_affiliation_strings":["Department of Informatics, The Graduate University for Advanced Studies (SOKENDAI), Tokyo, Japan","National Institute of Informatics, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, The Graduate University for Advanced Studies (SOKENDAI), Tokyo, Japan","institution_ids":["https://openalex.org/I200475212"]},{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5057299724"],"corresponding_institution_ids":["https://openalex.org/I184597095","https://openalex.org/I200475212"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.8741,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77457117,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"11","issue":null,"first_page":"17116","last_page":"17137"},"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/T10260","display_name":"Software Engineering Research","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9854999780654907,"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/hyperparameter","display_name":"Hyperparameter","score":0.8672314882278442},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7831768989562988},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7126073241233826},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.622140109539032},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5904123187065125},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5728842616081238},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5248717665672302},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.49247679114341736},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.47288742661476135},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4668935537338257},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4264053404331207},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12940144538879395},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12894701957702637},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.12366771697998047},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08465465903282166}],"concepts":[{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.8672314882278442},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7831768989562988},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7126073241233826},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.622140109539032},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5904123187065125},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5728842616081238},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5248717665672302},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.49247679114341736},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.47288742661476135},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4668935537338257},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4264053404331207},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12940144538879395},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12894701957702637},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.12366771697998047},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08465465903282166},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2023.3246267","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3246267","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10047888.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:188bcae17839430abf6a2e41c3bf08b6","is_oa":true,"landing_page_url":"https://doaj.org/article/188bcae17839430abf6a2e41c3bf08b6","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 11, Pp 17116-17137 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3246267","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3246267","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10047888.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1978762350","display_name":null,"funder_award_id":"JPMJCR21D4","funder_id":"https://openalex.org/F4320334789","funder_display_name":"Japan Science and Technology Agency"}],"funders":[{"id":"https://openalex.org/F4320334789","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4321021831.pdf","grobid_xml":"https://content.openalex.org/works/W4321021831.grobid-xml"},"referenced_works_count":65,"referenced_works":["https://openalex.org/W1501005121","https://openalex.org/W1522301498","https://openalex.org/W1553476745","https://openalex.org/W2086161653","https://openalex.org/W2097381042","https://openalex.org/W2103104224","https://openalex.org/W2106261932","https://openalex.org/W2107297861","https://openalex.org/W2109910161","https://openalex.org/W2111316871","https://openalex.org/W2122410182","https://openalex.org/W2130750514","https://openalex.org/W2156869222","https://openalex.org/W2161009228","https://openalex.org/W2164114810","https://openalex.org/W2202549229","https://openalex.org/W2462906003","https://openalex.org/W2492794003","https://openalex.org/W2788455270","https://openalex.org/W2792217087","https://openalex.org/W2792643794","https://openalex.org/W2837981523","https://openalex.org/W2949676527","https://openalex.org/W2964227312","https://openalex.org/W2973007837","https://openalex.org/W2984187004","https://openalex.org/W2990138404","https://openalex.org/W3039116038","https://openalex.org/W3138984732","https://openalex.org/W3174288549","https://openalex.org/W4211221179","https://openalex.org/W4214717370","https://openalex.org/W4293872189","https://openalex.org/W6616173779","https://openalex.org/W6631190155","https://openalex.org/W6637770816","https://openalex.org/W6638088447","https://openalex.org/W6640679069","https://openalex.org/W6674600207","https://openalex.org/W6674812091","https://openalex.org/W6677088747","https://openalex.org/W6682205418","https://openalex.org/W6683195989","https://openalex.org/W6683204974","https://openalex.org/W6684159546","https://openalex.org/W6684921986","https://openalex.org/W6718092244","https://openalex.org/W6718836005","https://openalex.org/W6730885009","https://openalex.org/W6734215269","https://openalex.org/W6739585900","https://openalex.org/W6740801417","https://openalex.org/W6748599296","https://openalex.org/W6749029207","https://openalex.org/W6752338937","https://openalex.org/W6753060773","https://openalex.org/W6756303580","https://openalex.org/W6762729159","https://openalex.org/W6766978945","https://openalex.org/W6767317771","https://openalex.org/W6767649332","https://openalex.org/W6767862010","https://openalex.org/W6774122581","https://openalex.org/W6780559895","https://openalex.org/W6790486821"],"related_works":["https://openalex.org/W4281847915","https://openalex.org/W3000635674","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W3099153698","https://openalex.org/W4297873223"],"abstract_inverted_index":{"Human":[0],"knowledge":[1],"can":[2],"reduce":[3],"the":[4,15,91,98,133,141,160,163,167,171,178,181,189,195,216,230,265],"number":[5,232],"of":[6,39,51,65,94,156,191,233],"iterations":[7],"required":[8],"to":[9,24,81,140,169,187,221,264],"learn":[10],"in":[11,27,254,268],"reinforcement":[12,204],"learning.":[13,118,173],"Though":[14],"most":[16],"common":[17],"approach":[18],"uses":[19],"trajectories,":[20],"it":[21,77],"is":[22,44,62,78,101,121,137,242,262],"difficult":[23],"acquire":[25],"them":[26],"certain":[28],"domains.":[29],"Subgoals,":[30],"which":[31,61],"are":[32,219],"intermediate":[33],"states,":[34],"have":[35],"been":[36],"studied":[37],"instead":[38],"trajectories.":[40],"Subgoal-based":[41],"reward":[42,56,67,92,99,125,142],"shaping":[43,68],"a":[45,49,63,70,83,111,154,202],"reward-shaping":[46,209],"framework":[47],"with":[48,153,201,225],"sequence":[50,155],"subgoals":[52,157,218,222,234],"based":[53],"on":[54,90],"potential-based":[55,66],"shaping.":[57],"The":[58,211],"potential":[59,116,168,249,261,267],"function":[60,93,100],"component":[64],"has":[69],"hyperparameter":[71,84,112],"that":[72,109,215,238,247,259],"controls":[73],"its":[74,86,115,130,198],"output.":[75],"However,":[76],"not":[79],"easy":[80],"select":[82],"because":[85],"appropriate":[87,231],"value":[88,120,161,172],"depends":[89],"an":[95,122,127,149],"environment,":[96],"and":[97,113,136,158,194,207,258,271],"unknown.":[102],"We":[103,184,228],"propose":[104],"<italic":[105],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[106],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">learned":[107],"potential</i>":[108],"parameterizes":[110],"acquires":[114],"through":[117],"A":[119],"expected":[123],"accumulated":[124],"if":[126],"agent":[128],"follows":[129],"policy":[131],"after":[132],"current":[134],"state":[135,151],"strongly":[138],"related":[139],"function.":[143],"With":[144],"learned":[145,192,226,236,245,248,260],"potential,":[146,193,237,246],"we":[147],"build":[148],"abstract":[150,164,182],"space":[152],"use":[159],"over":[162,180],"states":[165],"as":[166],"accelerate":[170],"N-step":[174],"TD":[175],"learning":[176,205,252],"learns":[177],"values":[179],"state.":[183],"conducted":[185],"experiments":[186],"evaluate":[188],"effectiveness":[190,199],"results":[196,212],"indicate":[197,214],"compared":[200],"baseline":[203],"algorithm":[206],"several":[208],"algorithms.":[210],"also":[213],"participants\u2019":[217],"superior":[220,263],"generated":[223],"randomly":[224],"potential.":[227],"discuss":[229],"for":[235,244],"partially":[239],"ordered":[240],"subgoal":[241],"helpful":[243],"cannot":[250],"make":[251],"efficient":[253],"step":[255],"penalized":[256],"rewards,":[257],"non-learned":[266],"mixed":[269],"positive":[270],"negative":[272],"rewards.":[273]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}