{"id":"https://openalex.org/W3131966701","doi":null,"title":"Improved Context-Based Offline Meta-RL with Attention and Contrastive Learning.","display_name":"Improved Context-Based Offline Meta-RL with Attention and Contrastive Learning.","publication_year":2021,"publication_date":"2021-02-22","ids":{"openalex":"https://openalex.org/W3131966701","mag":"3131966701"},"language":"en","primary_location":{"id":"mag:3131966701","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2102.10774","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://export.arxiv.org/pdf/2102.10774","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067232825","display_name":"Lanqing Li","orcid":"https://orcid.org/0000-0003-1998-4022","observed_orcids":["https://orcid.org/0000-0003-1998-4022","https://orcid.org/0009-0006-4987-4536"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lanqing Li","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-1998-4022","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024043542","display_name":"Yuanhao Huang","orcid":"https://orcid.org/0000-0002-0147-908X","observed_orcids":["https://orcid.org/0000-0002-0147-908X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuanhao Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101186016","display_name":"Dijun Luo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dijun Luo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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":0.0003000000142492354,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/task-inference","display_name":"task inference","score":0.6880000233650208},{"id":"https://openalex.org/keywords/focal","display_name":"FOCAL","score":0.9580000042915344},{"id":"https://openalex.org/keywords/end-to-end-learning","display_name":"end-to-end learning","score":0.5239999890327454}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8455584049224854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.803575873374939},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6645926237106323},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6180249452590942},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6043729186058044},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5748106241226196},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5686212182044983},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.532908022403717},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4303663969039917},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.43019479513168335},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3131966701","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2102.10774","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3131966701","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2102.10774","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2138621090","https://openalex.org/W2145339207","https://openalex.org/W2147527908","https://openalex.org/W2158782408","https://openalex.org/W2187089797","https://openalex.org/W2530849036","https://openalex.org/W2550182557","https://openalex.org/W2578206533","https://openalex.org/W2604763608","https://openalex.org/W2626778328","https://openalex.org/W2766447205","https://openalex.org/W2766453196","https://openalex.org/W2781726626","https://openalex.org/W2787501667","https://openalex.org/W2904730732","https://openalex.org/W2917551568","https://openalex.org/W2923504512","https://openalex.org/W2946567085","https://openalex.org/W2947150733","https://openalex.org/W2949879676","https://openalex.org/W2963341956","https://openalex.org/W2963581679","https://openalex.org/W2966537656","https://openalex.org/W2982316857","https://openalex.org/W2991355586","https://openalex.org/W2994066474","https://openalex.org/W2994871715","https://openalex.org/W2996896271","https://openalex.org/W3005680577","https://openalex.org/W3015230978","https://openalex.org/W3022566517","https://openalex.org/W3035080282","https://openalex.org/W3035435378","https://openalex.org/W3035524453","https://openalex.org/W3092688116","https://openalex.org/W3117215073","https://openalex.org/W3125760305","https://openalex.org/W4297808394","https://openalex.org/W4302288054"],"related_works":["https://openalex.org/W3206435284","https://openalex.org/W4297809649","https://openalex.org/W3090106354","https://openalex.org/W4398192534","https://openalex.org/W6947401840","https://openalex.org/W4404710285","https://openalex.org/W4385392792","https://openalex.org/W4362598230","https://openalex.org/W4385654679","https://openalex.org/W4283332611"],"abstract_inverted_index":{"Meta-learning":[0],"for":[1,40,74],"offline":[2],"reinforcement":[3],"learning":[4,43,72,80],"(OMRL)":[5],"is":[6,28],"an":[7,48],"understudied":[8],"problem":[9,27],"with":[10],"tremendous":[11],"potential":[12],"impact":[13],"by":[14,64],"enabling":[15],"RL":[16],"algorithms":[17,107],"in":[18],"many":[19],"real-world":[20],"applications.":[21],"A":[22],"popular":[23],"solution":[24],"to":[25,29,89,105],"the":[26,59,91],"infer":[30],"task":[31,45,77],"identity":[32],"as":[33],"augmented":[34],"state":[35],"using":[36],"a":[37],"context-based":[38],"encoder,":[39],"which":[41],"efficient":[42],"of":[44,58,81,97],"representations":[46],"remains":[47],"open":[49],"challenge.":[50],"In":[51],"this":[52],"work,":[53],"we":[54],"improve":[55],"upon":[56],"one":[57],"SOTA":[60],"OMRL":[61],"algorithms,":[62],"FOCAL,":[63],"incorporating":[65],"intra-task":[66],"attention":[67],"mechanism":[68],"and":[69,79,85,95,100],"inter-task":[70],"contrastive":[71],"objectives":[73],"more":[75],"effective":[76],"inference":[78],"control.":[82],"Theoretical":[83],"analysis":[84],"experiments":[86],"are":[87],"presented":[88],"demonstrate":[90],"superior":[92],"performance,":[93],"efficiency":[94],"robustness":[96],"our":[98],"end-to-end":[99],"model":[101],"free":[102],"method":[103],"compared":[104],"prior":[106],"across":[108],"multiple":[109],"meta-RL":[110],"benchmarks.":[111]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2021-03-01T00:00:00"}