{"id":"https://openalex.org/W4409363547","doi":"https://doi.org/10.1609/aaai.v39i18.34097","title":"Visual Reinforcement Learning with Residual Action","display_name":"Visual Reinforcement Learning with Residual Action","publication_year":2025,"publication_date":"2025-04-11","ids":{"openalex":"https://openalex.org/W4409363547","doi":"https://doi.org/10.1609/aaai.v39i18.34097"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v39i18.34097","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i18.34097","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/34097/36252","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/34097/36252","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049272791","display_name":"Zhenxian Liu","orcid":"https://orcid.org/0000-0003-2617-7077"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenxian Liu","raw_affiliation_strings":["National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070755370","display_name":"Peixi Peng","orcid":"https://orcid.org/0000-0002-7427-8764"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peixi Peng","raw_affiliation_strings":["School of Electronic and Computer Engineering, Shenzhen Graduate School, Peking University, China\nPeng Cheng Laboratory, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Shenzhen Graduate School, Peking University, China\nPeng Cheng Laboratory, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023918894","display_name":"Yonghong Tian","orcid":"https://orcid.org/0000-0002-2978-5935"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghong Tian","raw_affiliation_strings":["National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, China\nSchool of Electronic and Computer Engineering, Shenzhen Graduate School, Peking University, China\nPeng Cheng Laboratory, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, China\nSchool of Electronic and Computer Engineering, Shenzhen Graduate School, Peking University, China\nPeng Cheng Laboratory, China","institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"39","issue":"18","first_page":"19050","last_page":"19058"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.8543000221252441,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.8543000221252441,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10427","display_name":"Visual perception and processing mechanisms","score":0.7465000152587891,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10914","display_name":"Tactile and Sensory Interactions","score":0.7168999910354614,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6941910982131958},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6018138527870178},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5987004041671753},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5133523344993591},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.42023152112960815},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40088242292404175},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3855621814727783},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.35345545411109924},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.12364479899406433},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0616183876991272}],"concepts":[{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6941910982131958},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6018138527870178},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5987004041671753},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5133523344993591},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42023152112960815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40088242292404175},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3855621814727783},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.35345545411109924},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.12364479899406433},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0616183876991272},{"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/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v39i18.34097","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i18.34097","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/34097/36252","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"}],"best_oa_location":{"id":"doi:10.1609/aaai.v39i18.34097","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i18.34097","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/34097/36252","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/G1947953275","display_name":null,"funder_award_id":"62425101","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3833898155","display_name":null,"funder_award_id":"62088102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4587952244","display_name":null,"funder_award_id":"62027804","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5150481254","display_name":null,"funder_award_id":"PCL2021A13","funder_id":"https://openalex.org/F4320318558","funder_display_name":"Peng Cheng Laboratory"},{"id":"https://openalex.org/G5151253548","display_name":null,"funder_award_id":"62332002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8687311786","display_name":null,"funder_award_id":"62372010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320318558","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409363547.pdf","grobid_xml":"https://content.openalex.org/works/W4409363547.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Learning":[0,88],"control":[1,83,136],"policy":[2,37,122],"from":[3,112],"continuous":[4],"action":[5,79],"space":[6],"by":[7,35],"visual":[8],"observations":[9],"is":[10,23],"a":[11],"fundamental":[12],"and":[13,61,85,124,144,156],"challenging":[14],"task":[15],"in":[16,81],"reinforcement":[17],"learning":[18,69,74,109],"(RL).":[19],"An":[20],"essential":[21],"problem":[22],"how":[24],"to":[25,31,93,130],"accurately":[26],"map":[27],"the":[28,32,36,47,51,68,73,78,96,102,118,121,134,148],"high-dimensional":[29],"images":[30],"optimal":[33,54],"actions":[34,43,55,99,110],"network.":[38],"Traditional":[39],"decision-making":[40],"modules":[41],"output":[42,119],"solely":[44],"based":[45,100],"on":[46,58,101,140],"current":[48],"observation,":[49],"while":[50],"distributions":[52],"of":[53,98,120],"are":[56],"dependent":[57],"specific":[59],"tasks":[60],"cannot":[62],"be":[63],"known":[64],"priorly,":[65],"which":[66],"increases":[67],"difficulty.":[70],"To":[71],"make":[72],"easier,":[75],"we":[76],"analyze":[77],"characteristics":[80],"several":[82],"tasks,":[84],"propose":[86],"Reinforcement":[87],"with":[89],"Residual":[90],"Action":[91],"(ResAct)":[92],"explicitly":[94],"model":[95],"adjustments":[97],"differences":[103],"between":[104],"adjacent":[105],"observations,":[106],"rather":[107],"than":[108],"directly":[111],"observations.":[113],"The":[114],"method":[115,149],"just":[116],"redefines":[117],"network,":[123],"doesn\u2019t":[125],"introduce":[126],"any":[127],"prior":[128],"assumption":[129],"constrain":[131],"or":[132],"simplify":[133],"vanilla":[135],"problem.":[137],"Extensive":[138],"experiments":[139],"DeepMind":[141],"Control":[142],"Suite":[143],"CARLA":[145],"demonstrate":[146],"that":[147],"could":[150],"improve":[151],"different":[152],"RL":[153],"baselines":[154],"significantly,":[155],"achieve":[157],"state-of-the-art":[158],"performance.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}