{"id":"https://openalex.org/W4285601736","doi":"https://doi.org/10.24963/ijcai.2022/437","title":"Self-Predictive Dynamics for Generalization of Vision-based Reinforcement Learning","display_name":"Self-Predictive Dynamics for Generalization of Vision-based Reinforcement Learning","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4285601736","doi":"https://doi.org/10.24963/ijcai.2022/437"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/437","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/437","pdf_url":"https://www.ijcai.org/proceedings/2022/0437.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2022/0437.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100719026","display_name":"Kyung\u2010Soo Kim","orcid":"https://orcid.org/0000-0002-7738-2284"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyungsoo Kim","raw_affiliation_strings":["Sungkyunkwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sungkyunkwan University","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001904744","display_name":"Jeongsoo Ha","orcid":"https://orcid.org/0000-0001-7963-0571"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jeongsoo Ha","raw_affiliation_strings":["Sungkyunkwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sungkyunkwan University","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101688828","display_name":"Yusung Kim","orcid":"https://orcid.org/0000-0002-9306-8738"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yusung Kim","raw_affiliation_strings":["Sungkyunkwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sungkyunkwan University","institution_ids":["https://openalex.org/I848706"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5191,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.62491386,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3150","last_page":"3156"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T10603","display_name":"Smart Grid Energy Management","score":0.964900016784668,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.963100016117096,"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/generalization","display_name":"Generalization","score":0.8249411582946777},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7682015895843506},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7091963291168213},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6978753805160522},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6518322229385376},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6144710183143616},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.6034277677536011},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5828903913497925},{"id":"https://openalex.org/keywords/inverse-dynamics","display_name":"Inverse dynamics","score":0.5656228065490723},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4139983355998993},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3947116732597351},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1023603081703186}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.8249411582946777},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7682015895843506},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7091963291168213},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6978753805160522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6518322229385376},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6144710183143616},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.6034277677536011},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5828903913497925},{"id":"https://openalex.org/C187523126","wikidata":"https://www.wikidata.org/wiki/Q17098330","display_name":"Inverse dynamics","level":3,"score":0.5656228065490723},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4139983355998993},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3947116732597351},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1023603081703186},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2022/437","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/437","pdf_url":"https://www.ijcai.org/proceedings/2022/0437.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/437","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/437","pdf_url":"https://www.ijcai.org/proceedings/2022/0437.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2191473729","display_name":null,"funder_award_id":"2019-0-00421","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G3697634776","display_name":null,"funder_award_id":"2020-0-00973","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4296643599","display_name":null,"funder_award_id":"2022-0-01045","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"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/G5080715506","display_name":null,"funder_award_id":"2019-0-00421","funder_id":"https://openalex.org/F4320321378","funder_display_name":"Sungkyunkwan University"},{"id":"https://openalex.org/G638615795","display_name":null,"funder_award_id":"2020-0-00973","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G8874964841","display_name":null,"funder_award_id":"2019-0-00421","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320321378","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20"},{"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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285601736.pdf","grobid_xml":"https://content.openalex.org/works/W4285601736.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W2619947201","https://openalex.org/W2736601468","https://openalex.org/W2781585732","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2963523627","https://openalex.org/W2964121592","https://openalex.org/W2977481643","https://openalex.org/W2997103132","https://openalex.org/W3005680577","https://openalex.org/W3021708257","https://openalex.org/W3041404693","https://openalex.org/W3115293622","https://openalex.org/W3125947392","https://openalex.org/W3172628684","https://openalex.org/W3205321526","https://openalex.org/W4287724327","https://openalex.org/W4287811291","https://openalex.org/W4288294128","https://openalex.org/W4289294484","https://openalex.org/W4295719664","https://openalex.org/W4297789758","https://openalex.org/W4297808394"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W3162204513","https://openalex.org/W2138720691","https://openalex.org/W400207537","https://openalex.org/W1487930919","https://openalex.org/W1974966543","https://openalex.org/W2550974801","https://openalex.org/W4205272379","https://openalex.org/W1519970984","https://openalex.org/W2184783674"],"abstract_inverted_index":{"Vision-based":[0],"reinforcement":[1],"learning":[2],"requires":[3],"efficient":[4],"and":[5,23,58,63,69,85,98],"robust":[6],"representations":[7,65],"of":[8,80],"image-based":[9],"observations,":[10,97],"especially":[11],"when":[12],"the":[13,73,101],"images":[14],"contain":[15],"distracting":[16],"(task-irrelevant)":[17],"elements":[18],"such":[19],"as":[20],"shadows,":[21],"clouds,":[22],"light.":[24],"It":[25],"becomes":[26],"more":[27],"important":[28],"if":[29],"those":[30],"distractions":[31],"are":[32],"not":[33],"exposed":[34],"during":[35],"training.":[36,54],"We":[37],"design":[38],"a":[39,78],"Self-Predictive":[40],"Dynamics":[41],"(SPD)":[42],"method":[43],"to":[44],"extract":[45],"task-relevant":[46],"features":[47],"efficiently,":[48],"even":[49],"in":[50,61,95],"unseen":[51,105],"observations":[52],"after":[53],"SPD":[55,91],"uses":[56],"weak":[57],"strong":[59],"augmentations":[60],"parallel,":[62],"learns":[64],"by":[66],"predicting":[67],"inverse":[68],"forward":[70],"transitions":[71],"across":[72],"two-way":[74],"augmented":[75],"versions.":[76],"In":[77],"set":[79],"MuJoCo":[81],"visual":[82],"control":[83],"tasks":[84],"an":[86],"autonomous":[87],"driving":[88],"task":[89],"(CARLA),":[90],"outperforms":[92],"previous":[93],"studies":[94],"complex":[96],"significantly":[99],"improves":[100],"generalization":[102],"performance":[103],"for":[104],"observations.":[106],"Our":[107],"code":[108],"is":[109],"available":[110],"at":[111],"https://github.com/unigary/SPD.":[112]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}