{"id":"https://openalex.org/W4385767913","doi":"https://doi.org/10.24963/ijcai.2023/432","title":"SeRO: Self-Supervised Reinforcement Learning for Recovery from Out-of-Distribution Situations","display_name":"SeRO: Self-Supervised Reinforcement Learning for Recovery from Out-of-Distribution Situations","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385767913","doi":"https://doi.org/10.24963/ijcai.2023/432"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/432","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/432","pdf_url":"https://www.ijcai.org/proceedings/2023/0432.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0432.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100728732","display_name":"Chan Kim","orcid":"https://orcid.org/0000-0003-1642-6789"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chan Kim","raw_affiliation_strings":["Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062735425","display_name":"Jaekyung Cho","orcid":"https://orcid.org/0000-0002-1835-534X"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaekyung Cho","raw_affiliation_strings":["Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081869234","display_name":"Christophe Bobda","orcid":"https://orcid.org/0000-0002-9042-9470"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Christophe Bobda","raw_affiliation_strings":["University of Florida"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florida","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048311228","display_name":"Seung\u2010Woo Seo","orcid":"https://orcid.org/0000-0003-4890-8563"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seung-Woo Seo","raw_affiliation_strings":["Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101807134","display_name":"Seong-Woo Kim","orcid":"https://orcid.org/0000-0003-1633-573X"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seong-Woo Kim","raw_affiliation_strings":["Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5081869234"],"corresponding_institution_ids":["https://openalex.org/I33213144"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3884","last_page":"3892"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T12761","display_name":"Data Stream Mining Techniques","score":0.996399998664856,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9932000041007996,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.797505259513855},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6591161489486694},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6163066029548645},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.45261862874031067},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4363267123699188},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33107560873031616},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16744667291641235},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13332781195640564},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.05679193139076233}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.797505259513855},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6591161489486694},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6163066029548645},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.45261862874031067},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4363267123699188},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33107560873031616},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16744667291641235},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13332781195640564},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.05679193139076233},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.24963/ijcai.2023/432","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/432","pdf_url":"https://www.ijcai.org/proceedings/2023/0432.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2311.03651","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.03651","pdf_url":"https://arxiv.org/pdf/2311.03651","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/432","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/432","pdf_url":"https://www.ijcai.org/proceedings/2023/0432.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1141365172","display_name":null,"funder_award_id":"2021R1A2C1093957","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G3443648609","display_name":null,"funder_award_id":"P0008747","funder_id":"https://openalex.org/F4320322064","funder_display_name":"Korea Institute for Advancement of Technology"},{"id":"https://openalex.org/G4078088329","display_name":null,"funder_award_id":"2021R1A2C1093957","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G7472325069","display_name":null,"funder_award_id":"P0008747","funder_id":"https://openalex.org/F4320321681","funder_display_name":"Ministry of Trade, Industry and Energy"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320321292","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542"},{"id":"https://openalex.org/F4320321681","display_name":"Ministry of Trade, Industry and Energy","ror":"https://ror.org/008nkqk13"},{"id":"https://openalex.org/F4320322064","display_name":"Korea Institute for Advancement of Technology","ror":"https://ror.org/015w1qa96"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320336769","display_name":"Institute of Engineering Research, Seoul National University","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385767913.pdf"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W2249585788","https://openalex.org/W2462906003","https://openalex.org/W2575705757","https://openalex.org/W2586067474","https://openalex.org/W2726187156","https://openalex.org/W2781726626","https://openalex.org/W2904453761","https://openalex.org/W2910781732","https://openalex.org/W2947150733","https://openalex.org/W2963780574","https://openalex.org/W2968104655","https://openalex.org/W2981030070","https://openalex.org/W2991355586","https://openalex.org/W3022566517","https://openalex.org/W3033324992","https://openalex.org/W3102100346","https://openalex.org/W3104574805","https://openalex.org/W3150718622","https://openalex.org/W3170059879","https://openalex.org/W4225937903","https://openalex.org/W4226345898","https://openalex.org/W4280553623","https://openalex.org/W4283319080","https://openalex.org/W4287066693"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Robotic":[0],"agents":[1,50,57,96],"trained":[2],"using":[3],"reinforcement":[4],"learning":[5],"have":[6],"the":[7,37,75,122,138,141,152],"problem":[8],"of":[9,132,137],"taking":[10],"unreliable":[11,44,84],"actions":[12,45],"in":[13,23,66,102,130],"an":[14],"out-of-distribution":[15],"(OOD)":[16],"state.":[17],"Agents":[18],"can":[19,150],"easily":[20],"become":[21],"OOD":[22,67,100,110,128,157],"real-world":[24],"environments":[25],"because":[26],"it":[27],"is":[28],"almost":[29],"impossible":[30],"for":[31,94,140],"them":[32],"to":[33,61,72,74,82,97,125,154,165],"visit":[34,166],"and":[35,69,135,170],"learn":[36,70],"entire":[38],"state":[39,77],"space":[40],"during":[41],"training.":[42],"Unfortunately,":[43],"do":[46],"not":[47],"ensure":[48],"that":[49,117,147],"perform":[51],"their":[52],"original":[53,142],"tasks":[54],"successfully.":[55],"Therefore,":[56],"should":[58],"be":[59],"able":[60],"recognize":[62],"whether":[63],"they":[64,107],"are":[65,163,173],"states":[68,162],"how":[71],"return":[73],"learned":[76],"distribution":[78],"rather":[79],"than":[80],"continue":[81],"take":[83],"actions.":[85],"In":[86],"this":[87],"study,":[88],"we":[89,145],"propose":[90],"a":[91,103],"novel":[92],"method":[93,119,149],"retraining":[95],"recover":[98,126,155],"from":[99,127,156],"situations":[101,129,158],"self-supervised":[104],"manner":[105],"when":[106,160],"fall":[108],"into":[109],"states.":[111],"Our":[112],"in-depth":[113],"experimental":[114],"results":[115],"demonstrate":[116],"our":[118,148],"substantially":[120],"improves":[121],"agent\u2019s":[123],"ability":[124],"terms":[131],"sample":[133],"efficiency":[134],"restoration":[136],"performance":[139],"tasks.":[143],"Moreover,":[144],"show":[146],"retrain":[151],"agent":[153],"even":[159],"in-distribution":[161],"difficult":[164],"through":[167],"exploration.":[168],"Code":[169],"supplementary":[171],"materials":[172],"available":[174],"at":[175],"https://github.com/SNUChanKim/SeRO.":[176]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2023-08-12T00:00:00"}