{"id":"https://openalex.org/W7137959146","doi":"https://doi.org/10.1609/aaai.v40i27.39432","title":"Enhancing Control Policy Smoothness by Aligning Actions with Predictions from Preceding States","display_name":"Enhancing Control Policy Smoothness by Aligning Actions with Predictions from Preceding States","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137959146","doi":"https://doi.org/10.1609/aaai.v40i27.39432"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i27.39432","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i27.39432","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39432/43393","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39432/43393","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123995350","display_name":"Kyoleen Kwak","orcid":null},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Kyoleen Kwak","raw_affiliation_strings":["Kyung Hee University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyung Hee University","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129724215","display_name":"Hyoseok Hwang","orcid":null},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyoseok Hwang","raw_affiliation_strings":["Kyung Hee University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyung Hee University","institution_ids":["https://openalex.org/I35928602"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5123995350"],"corresponding_institution_ids":["https://openalex.org/I35928602"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1616738,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"27","first_page":"22707","last_page":"22715"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.838699996471405,"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":0.838699996471405,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.022700000554323196,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.01140000019222498,"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/smoothing","display_name":"Smoothing","score":0.720300018787384},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6965000033378601},{"id":"https://openalex.org/keywords/smoothness","display_name":"Smoothness","score":0.6933000087738037},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5593000054359436},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.531000018119812},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5199999809265137}],"concepts":[{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.720300018787384},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6965000033378601},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.6933000087738037},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6905999779701233},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5593000054359436},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.531000018119812},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5199999809265137},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.49959999322891235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4699000120162964},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33980000019073486},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3197000026702881},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3005000054836273},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.29019999504089355},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.26409998536109924}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i27.39432","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i27.39432","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39432/43393","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/39432","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/39432","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i27.39432","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i27.39432","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39432/43393","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2443203484","display_name":null,"funder_award_id":"IITP-2023-RS-2023-00266615","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G3872958509","display_name":null,"funder_award_id":"RS-2022-00155911","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G4700831490","display_name":null,"funder_award_id":"2022-","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4932531269","display_name":null,"funder_award_id":"RS-2022-00155911","funder_id":"https://openalex.org/F4320321332","funder_display_name":"Kyung Hee University"},{"id":"https://openalex.org/G585115220","display_name":null,"funder_award_id":"RS-2022-00155911","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320321332","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218"},{"id":"https://openalex.org/F4320321681","display_name":"Ministry of Trade, Industry and Energy","ror":"https://ror.org/008nkqk13"},{"id":"https://openalex.org/F4320324891","display_name":"Iran Telecommunication Research Center","ror":"https://ror.org/01a3g2z22"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137959146.pdf","grobid_xml":"https://content.openalex.org/works/W7137959146.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2],"has":[3],"proven":[4],"to":[5,10,22,51,58,158],"be":[6],"a":[7,70,76],"powerful":[8],"approach":[9],"solving":[11],"control":[12,173],"tasks,":[13],"but":[14],"its":[15],"characteristic":[16],"high\u2011frequency":[17],"oscillations":[18,33],"make":[19],"it":[20,98,107],"difficult":[21],"apply":[23],"in":[24,149,163],"real\u2011world":[25],"environments.":[26],"While":[27],"prior":[28],"methods":[29],"have":[30],"addressed":[31],"action":[32,53,130,136,140],"via":[34],"architectural":[35],"or":[36,45],"loss-based":[37,72],"methods,":[38],"the":[39,61,87,94,144],"latter":[40],"typically":[41],"depend":[42],"on":[43],"heuristic":[44],"synthetic":[46],"definitions":[47],"of":[48,89],"state":[49,83],"similarity":[50],"promote":[52],"consistency,":[54],"which":[55],"often":[56],"fail":[57],"accurately":[59],"reflect":[60],"underlying":[62],"system":[63,110],"dynamics.":[64,111],"In":[65],"this":[66,114],"paper,":[67],"we":[68,116],"propose":[69],"novel":[71],"method":[73,132],"by":[74,120,142,154],"introducing":[75],"transition-induced":[77,81,150],"similar":[78,82,151],"state.":[79,96],"The":[80],"is":[84],"defined":[85],"as":[86],"distribution":[88],"next":[90],"states":[91,152],"transitioned":[92],"from":[93,125],"previous":[95],"Since":[97],"utilizes":[99],"only":[100],"environmental":[101],"feedback":[102],"and":[103,153,165,174],"actually":[104],"collected":[105],"data,":[106],"better":[108],"captures":[109],"Building":[112],"upon":[113],"foundation,":[115],"introduce":[117],"Action":[118],"Smoothing":[119],"Aligning":[121],"Actions":[122],"with":[123,146],"Predictions":[124],"Preceding":[126],"States":[127],"(ASAP),":[128],"an":[129],"smoothing":[131],"that":[133,169],"effectively":[134],"mitigates":[135],"oscillations.":[137,161],"ASAP":[138,170],"enforces":[139],"smoothness":[141],"aligning":[143],"actions":[145],"those":[147],"taken":[148],"penalizing":[155],"second-order":[156],"differences":[157],"suppress":[159],"high-frequency":[160],"Experiments":[162],"Gymnasium":[164],"Isaac-lab":[166],"environments":[167],"demonstrate":[168],"yields":[171],"smoother":[172],"improved":[175],"policy":[176],"performance":[177],"over":[178],"existing":[179],"methods.":[180]},"counts_by_year":[],"updated_date":"2026-06-08T08:47:23.578185","created_date":"2026-03-18T00:00:00"}