{"id":"https://openalex.org/W7138392797","doi":"https://doi.org/10.1609/aaai.v40i26.39313","title":"Improving Generalization in Offline Meta-Reinforcement Learning via Cross-task Contexts","display_name":"Improving Generalization in Offline Meta-Reinforcement Learning via Cross-task Contexts","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138392797","doi":"https://doi.org/10.1609/aaai.v40i26.39313"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i26.39313","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i26.39313","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39313/43274","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39313/43274","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129656660","display_name":"Hongcai He","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongcai He","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088728950","display_name":"Zetao Zheng","orcid":"https://orcid.org/0000-0002-7801-0378"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zetao Zheng","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China\nSichuan Artificial Intelligence Research Institute, Yibin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China\nSichuan Artificial Intelligence Research Institute, Yibin, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108632549","display_name":"Anjie Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Anjie Zhu","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065413088","display_name":"Deqiang Ouyang","orcid":"https://orcid.org/0000-0003-2259-886X"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deqiang Ouyang","raw_affiliation_strings":["Chongqing University, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129670175","display_name":"Jie Shao","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Shao","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China\nSichuan Artificial Intelligence Research Institute, Yibin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China\nSichuan Artificial Intelligence Research Institute, Yibin, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.52279202,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"26","first_page":"21637","last_page":"21644"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.5680000185966492,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.5680000185966492,"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":0.22949999570846558,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.04470000043511391,"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":0.6480000019073486},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6407999992370605},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5504999756813049},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.545199990272522},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5375999808311462},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4659000039100647}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7390000224113464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6561999917030334},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6480000019073486},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6407999992370605},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5504999756813049},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.545199990272522},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5375999808311462},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.508400022983551},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4659000039100647},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.45969998836517334},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.337799996137619},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.3346000015735626},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3296999931335449},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.263700008392334}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i26.39313","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i26.39313","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39313/43274","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"},{"id":"pmh:oai:ojs.aaai.org:article/39313","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/39313","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i26.39313","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i26.39313","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39313/43274","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/G1882737025","display_name":null,"funder_award_id":"62276047","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4427435602","display_name":null,"funder_award_id":"CSTB2023NSCQ","funder_id":"https://openalex.org/F4320323172","funder_display_name":"Natural Science Foundation of Chongqing"},{"id":"https://openalex.org/G974182458","display_name":null,"funder_award_id":"CSTB2023NSCQ-MSX1020","funder_id":"https://openalex.org/F4320323172","funder_display_name":"Natural Science Foundation of Chongqing"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320323172","display_name":"Natural Science Foundation of Chongqing","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138392797.pdf","grobid_xml":"https://content.openalex.org/works/W7138392797.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Context-based":[0],"offline":[1,12,60],"meta-reinforcement":[2],"learning":[3,162],"(meta-RL)":[4],"is":[5,78],"a":[6,17,90,104,157],"paradigm":[7],"that":[8,64,163],"integrates":[9],"meta-learning":[10],"with":[11,131],"reinforcement":[13],"learning.":[14],"It":[15],"learns":[16],"strategy":[18,31],"to":[19,34,42,49,59,149,181],"extract":[20],"task-specific":[21,112],"contexts":[22,45,94,113,128,142,177],"from":[23,54],"trajectories":[24],"of":[25,84,114,167,176,193],"meta-training":[26,115],"tasks":[27,116,153],"and":[28,178],"leverages":[29],"this":[30],"for":[32,46,80,95,159],"adapting":[33],"unseen":[35,182],"target":[36,183],"tasks.":[37,126,139,184],"However,":[38],"existing":[39,196],"methods":[40],"struggle":[41],"generate":[43],"generalizable":[44],"adaptations":[47],"due":[48],"context":[50,85,105],"shift,":[51],"which":[52,110],"arises":[53],"the":[55,66,82,122,165,174,190],"context-based":[56],"policy":[57],"overfitting":[58],"data.":[61],"We":[62],"argue":[63],"leveraging":[65],"internal":[67,123],"relationships":[68,124],"among":[69,125],"tasks,":[70,171],"rather":[71],"than":[72],"treating":[73],"each":[74],"task":[75],"in":[76,98,187],"isolation,":[77],"crucial":[79],"mitigating":[81],"impact":[83],"shift.":[86],"Hence,":[87],"we":[88,102],"propose":[89],"framework":[91],"called":[92],"cross-task":[93,141],"improving":[96,173],"generalization":[97,175],"meta-RL":[99],"(CTMRL).":[100],"Specifically,":[101],"design":[103],"quantization":[106],"variational":[107],"auto-encoder":[108],"(CQ-VAE),":[109],"clusters":[111],"into":[117],"discrete":[118],"codes":[119],"based":[120],"on":[121],"Cross-task":[127],"are":[129],"constructed":[130],"these":[132],"codes,":[133],"reflecting":[134],"shared":[135],"information":[136],"across":[137,152],"similar":[138,168],"These":[140],"not":[143],"only":[144],"serve":[145],"as":[146],"high-level":[147],"structures":[148],"capture":[150],"similarity":[151],"but":[154],"also":[155],"provide":[156],"foundation":[158],"hard":[160],"contrastive":[161],"enhances":[164],"distinguishability":[166],"yet":[169],"distinct":[170],"thereby":[172],"facilitating":[179],"adaptation":[180],"The":[185],"evaluation":[186],"meta-environments":[188],"confirms":[189],"performance":[191],"advantage":[192],"CTMRL":[194],"over":[195],"methods.":[197]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-18T00:00:00"}