{"id":"https://openalex.org/W4285172767","doi":"https://doi.org/10.1109/lra.2022.3186508","title":"Utilizing Hidden Observations to Enhance the Performance of the Trained Agent","display_name":"Utilizing Hidden Observations to Enhance the Performance of the Trained Agent","publication_year":2022,"publication_date":"2022-06-27","ids":{"openalex":"https://openalex.org/W4285172767","doi":"https://doi.org/10.1109/lra.2022.3186508"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2022.3186508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2022.3186508","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/A5070677616","display_name":"Sooyoung Jang","orcid":"https://orcid.org/0000-0002-6931-9592"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Sooyoung Jang","raw_affiliation_strings":["Intelligence Convergence Research Laboratory, Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-6931-9592","affiliations":[{"raw_affiliation_string":"Intelligence Convergence Research Laboratory, Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100343841","display_name":"Joohyung Lee","orcid":"https://orcid.org/0000-0003-1102-3905"},"institutions":[{"id":"https://openalex.org/I12832649","display_name":"Gachon University","ror":"https://ror.org/03ryywt80","country_code":"KR","type":"education","lineage":["https://openalex.org/I12832649"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joohyung Lee","raw_affiliation_strings":["School of Computing, Gachon University, Seongnam, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-1102-3905","affiliations":[{"raw_affiliation_string":"School of Computing, Gachon University, Seongnam, South Korea","institution_ids":["https://openalex.org/I12832649"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5070677616"],"corresponding_institution_ids":["https://openalex.org/I142401562"],"apc_list":null,"apc_paid":null,"fwci":0.1387,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53633502,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"7","issue":"3","first_page":"7858","last_page":"7864"},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9926999807357788,"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/notation","display_name":"Notation","score":0.649448573589325},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5506198406219482},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5496464967727661},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5336400270462036},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.5111921429634094},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5087485909461975},{"id":"https://openalex.org/keywords/hidden-variable-theory","display_name":"Hidden variable theory","score":0.46188491582870483},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3496916890144348},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3189713954925537},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.15846917033195496},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.12834110856056213}],"concepts":[{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.649448573589325},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5506198406219482},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5496464967727661},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5336400270462036},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.5111921429634094},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5087485909461975},{"id":"https://openalex.org/C137002209","wikidata":"https://www.wikidata.org/wiki/Q898521","display_name":"Hidden variable theory","level":3,"score":0.46188491582870483},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3496916890144348},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3189713954925537},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.15846917033195496},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.12834110856056213},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2022.3186508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2022.3186508","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6299999952316284,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G5626934565","display_name":null,"funder_award_id":"2021R1F1A1048098","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G828449615","display_name":null,"funder_award_id":"22ZR1100","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322093","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2073040595","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2538985812","https://openalex.org/W2604319603","https://openalex.org/W2605102581","https://openalex.org/W2733312032","https://openalex.org/W2736601468","https://openalex.org/W2754517384","https://openalex.org/W2962736495","https://openalex.org/W2963129648","https://openalex.org/W2963403143","https://openalex.org/W2996037775","https://openalex.org/W3021970402","https://openalex.org/W3126150352","https://openalex.org/W3150570724","https://openalex.org/W3188004887","https://openalex.org/W6717230150","https://openalex.org/W6728660318","https://openalex.org/W6733732937","https://openalex.org/W6741002519","https://openalex.org/W6777091672","https://openalex.org/W6780559895","https://openalex.org/W6790464592","https://openalex.org/W6801728237"],"related_works":["https://openalex.org/W2504004674","https://openalex.org/W2799327614","https://openalex.org/W2486541857","https://openalex.org/W2963177394","https://openalex.org/W1595229445","https://openalex.org/W4234886518","https://openalex.org/W2498744856","https://openalex.org/W4390482104","https://openalex.org/W322408318","https://openalex.org/W149041114"],"abstract_inverted_index":{"The":[0,130],"frame-skipping":[1,58],"strategy":[2,19],"has":[3],"been":[4],"widely":[5],"employed":[6],"in":[7,54,169,181],"deep":[8],"reinforcement":[9],"learning":[10],"(DRL)":[11],"technology":[12],"to":[13,122,150],"train":[14],"an":[15,146],"agent.":[16,129],"Specifically,":[17],"this":[18],"repeats":[20],"the":[21,25,39,45,57,64,70,81,87,110,124,127,154,163,166],"action":[22,46,72],"determined":[23],"by":[24,37,43],"agent":[26],"for":[27],"a":[28,75,101,178],"fixed":[29],"number":[30,40],"of":[31,41,83,126,165,171],"frames.":[32],"It":[33,140],"increases":[34],"computational":[35,93],"efficiency":[36],"reducing":[38],"inferences":[42],"making":[44],"decision":[47],"sparse.":[48],"However,":[49],"previously,":[50],"these":[51,97,106],"consecutive":[52],"changes":[53],"frames":[55,108],"during":[56,109,137],"were":[59],"hidden":[60,107,135,157],"and":[61,66,145,152,174],"ignored":[62],"from":[63,156],"environment":[65],"did":[67],"not":[68],"affect":[69,80],"agent\u2019s":[71],"decision.":[73],"As":[74],"result,":[76],"it":[77],"can":[78],"adversely":[79],"performance":[82,88,125,173],"trained":[84,128],"agents,":[85],"where":[86],"is":[89],"more":[90],"critical":[91],"than":[92],"efficiency.":[94],"To":[95],"alleviate":[96],"issues,":[98],"we":[99,161],"propose":[100],"new":[102],"framework":[103,132],"that":[104],"utilizes":[105],"frame-skipping,":[111],"called":[112],"<inline-formula":[113,117],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[114,118],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[115,119],"notation=\"LaTeX\">$hidden$</tex-math></inline-formula>":[116],"notation=\"LaTeX\">$observation$</tex-math></inline-formula>":[120],",":[121],"enhance":[123],"proposed":[131,167],"retrieves":[133],"all":[134],"observations":[136],"frame":[138],"skipping.":[139],"then":[141],"combines":[142],"batch":[143],"inference":[144],"exponentially":[147],"weighted":[148],"sum":[149],"calculate":[151],"merge":[153],"outputs":[155],"observations.":[158],"Through":[159],"experiments,":[160],"validated":[162],"effectiveness":[164],"method":[168],"terms":[170],"both":[172],"stability":[175],"with":[176],"only":[177],"marginal":[179],"increase":[180],"computation.":[182]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}