{"id":"https://openalex.org/W4380029620","doi":"https://doi.org/10.1109/icit58465.2023.10143045","title":"KeyState: Improving Image-based Reinforcement Learning with Keypoint for Robot Control","display_name":"KeyState: Improving Image-based Reinforcement Learning with Keypoint for Robot Control","publication_year":2023,"publication_date":"2023-04-04","ids":{"openalex":"https://openalex.org/W4380029620","doi":"https://doi.org/10.1109/icit58465.2023.10143045"},"language":"en","primary_location":{"id":"doi:10.1109/icit58465.2023.10143045","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icit58465.2023.10143045","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Industrial Technology (ICIT)","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/A5112933090","display_name":"Ling-Chen Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ling-Chen Chen","raw_affiliation_strings":["National Tsing Hua University,Department of Computer Science,Hsinchu,Taiwan","Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University,Department of Computer Science,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087938611","display_name":"Chi-Kai Ho","orcid":"https://orcid.org/0000-0002-2158-5947"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chi-Kai Ho","raw_affiliation_strings":["National Tsing Hua University,Department of Computer Science,Hsinchu,Taiwan","Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University,Department of Computer Science,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057871439","display_name":"Chung\u2010Ta King","orcid":"https://orcid.org/0000-0002-5041-5795"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chung-Ta King","raw_affiliation_strings":["National Tsing Hua University,Department of Computer Science,Hsinchu,Taiwan","Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University,Department of Computer Science,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I25846049"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05176893,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"31","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9925000071525574,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9672999978065491,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8732945919036865},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7593508958816528},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.749718189239502},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6941287517547607},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6848853230476379},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5929476618766785},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5803420543670654},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.562204897403717},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.49954891204833984},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.49834585189819336},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.49483102560043335},{"id":"https://openalex.org/keywords/robot-control","display_name":"Robot control","score":0.47608867287635803},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4721410572528839},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.41462385654449463},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.35593754053115845},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10993680357933044}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8732945919036865},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7593508958816528},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.749718189239502},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6941287517547607},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6848853230476379},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5929476618766785},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5803420543670654},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.562204897403717},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.49954891204833984},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.49834585189819336},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49483102560043335},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.47608867287635803},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4721410572528839},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.41462385654449463},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.35593754053115845},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10993680357933044},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icit58465.2023.10143045","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icit58465.2023.10143045","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Industrial Technology (ICIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G770833222","display_name":"Platform for Human Skill Transfer to Dual-Hand Human-Like Robots( I )","funder_award_id":"MOST109-2218-E007-023","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"}],"funders":[{"id":"https://openalex.org/F4320322795","display_name":"Ministry of Science and Technology, Taiwan","ror":"https://ror.org/02kv4zf79"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W2133665775","https://openalex.org/W2145339207","https://openalex.org/W2163614163","https://openalex.org/W2736601468","https://openalex.org/W2761873684","https://openalex.org/W2781585732","https://openalex.org/W2904246096","https://openalex.org/W2949678110","https://openalex.org/W2955368974","https://openalex.org/W2963009616","https://openalex.org/W2963305465","https://openalex.org/W2963419579","https://openalex.org/W2982697283","https://openalex.org/W2995298643","https://openalex.org/W3005680577","https://openalex.org/W3015437096","https://openalex.org/W3021708257","https://openalex.org/W3034487425","https://openalex.org/W3035524453","https://openalex.org/W3115293622","https://openalex.org/W3169196627","https://openalex.org/W3172115072","https://openalex.org/W3175558129","https://openalex.org/W3211941939","https://openalex.org/W4287811291","https://openalex.org/W4288294128","https://openalex.org/W4289294484","https://openalex.org/W4294226150","https://openalex.org/W4297808394","https://openalex.org/W4312554478","https://openalex.org/W6731293529","https://openalex.org/W6738746681","https://openalex.org/W6741002519","https://openalex.org/W6747387971","https://openalex.org/W6749972507","https://openalex.org/W6754539604","https://openalex.org/W6756256016","https://openalex.org/W6757592117","https://openalex.org/W6765407481","https://openalex.org/W6765456200","https://openalex.org/W6771217966","https://openalex.org/W6774314701","https://openalex.org/W6776867236","https://openalex.org/W6776901495","https://openalex.org/W6788616948","https://openalex.org/W6796163856","https://openalex.org/W6796852419","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W2930863966","https://openalex.org/W2126211886","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W2643884694","https://openalex.org/W2165180011","https://openalex.org/W1886477626","https://openalex.org/W4220829754","https://openalex.org/W2762381663","https://openalex.org/W4365788246"],"abstract_inverted_index":{"Learning":[0],"from":[1,125],"high-dimensional":[2],"images":[3,34],"is":[4,27,66,83,102,133],"essential":[5],"for":[6,51,68,142],"reinforcement":[7],"learning":[8],"(RL)":[9],"to":[10,28,35,61,109,119],"train":[11],"autonomous":[12],"agents":[13],"that":[14,39,154],"can":[15,47,92],"interact":[16],"directly":[17],"with":[18],"the":[19,33,41,75,84,87,97,100,111,114,121,155,166],"environment":[20],"using":[21],"visual":[22],"observations.":[23],"A":[24],"general":[25],"strategy":[26],"extract":[29,110],"task-relevant":[30],"information":[31,118],"in":[32,80],"learn":[36,62],"a":[37,58,139],"representation":[38],"characterizes":[40],"system":[42,63,78],"states.":[43],"Although":[44],"existing":[45],"works":[46],"find":[48],"good":[49],"representations":[50],"static":[52],"states":[53],"efficiently,":[54],"they":[55],"still":[56],"take":[57],"long":[59],"time":[60],"dynamics,":[64],"which":[65],"critical":[67],"applications":[69],"such":[70],"as":[71,116],"robot":[72,81,88,101,115],"control.":[73],"Since":[74],"most":[76],"important":[77],"dynamics":[79],"control":[82],"motions":[85],"of":[86,99,113,123,147,157],"itself,":[89],"image-based":[90],"RL":[91,124,148],"be":[93],"more":[94],"efficient":[95],"if":[96],"state":[98],"known.":[103],"In":[104],"this":[105],"paper,":[106],"we":[107],"propose":[108],"keypoints":[112],"auxiliary":[117],"improve":[120],"data-efficiency":[122,144],"image":[126],"pixels.":[127],"The":[128,150],"proposed":[129],"method,":[130],"called":[131],"KeyState,":[132],"evaluated":[134],"on":[135,160],"DeepMind":[136],"Control":[137],"Suite,":[138],"common":[140],"benchmark":[141],"evaluating":[143],"and":[145],"performance":[146,156],"agents.":[149],"experimental":[151],"results":[152],"show":[153],"KeyState":[158],"is,":[159],"average,":[161],"1.65":[162],"times":[163],"better":[164],"than":[165],"prior":[167],"pixel-based":[168],"methods.":[169]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}