{"id":"https://openalex.org/W4386908259","doi":"https://doi.org/10.48550/arxiv.2309.10790","title":"Guide Your Agent with Adaptive Multimodal Rewards","display_name":"Guide Your Agent with Adaptive Multimodal Rewards","publication_year":2023,"publication_date":"2023-09-19","ids":{"openalex":"https://openalex.org/W4386908259","doi":"https://doi.org/10.48550/arxiv.2309.10790"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2309.10790","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.10790","pdf_url":"https://arxiv.org/pdf/2309.10790","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2309.10790","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101777111","display_name":"Chang\u2010Yeon Kim","orcid":"https://orcid.org/0000-0002-7966-084X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kim, Changyeon","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009323476","display_name":"Younggyo Seo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seo, Younggyo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100458818","display_name":"Hao Liu","orcid":"https://orcid.org/0000-0002-5248-935X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Hao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101529103","display_name":"Lisa Lee","orcid":"https://orcid.org/0000-0001-5058-9464"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Lisa","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102928677","display_name":"Jinwoo Shin","orcid":"https://orcid.org/0000-0003-4313-4669"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shin, Jinwoo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108652283","display_name":"Honglak Lee","orcid":"https://orcid.org/0000-0002-1279-0068"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Honglak","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5033571780","display_name":"Kimin Lee","orcid":"https://orcid.org/0000-0001-9017-3084"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Kimin","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101777111"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9930999875068665,"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/T10028","display_name":"Topic Modeling","score":0.991599977016449,"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/computer-science","display_name":"Computer science","score":0.8185155987739563},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7174772024154663},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5793483257293701},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5784432888031006},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.5773850679397583},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.556209146976471},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5026097297668457},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4979567527770996},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4602109491825104},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4526588022708893},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.43031543493270874},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.42787569761276245},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4133411645889282},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.381375253200531},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11447656154632568},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.09763526916503906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8185155987739563},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7174772024154663},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5793483257293701},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5784432888031006},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.5773850679397583},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.556209146976471},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5026097297668457},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4979567527770996},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4602109491825104},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4526588022708893},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.43031543493270874},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.42787569761276245},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4133411645889282},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.381375253200531},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11447656154632568},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.09763526916503906},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","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},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2309.10790","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.10790","pdf_url":"https://arxiv.org/pdf/2309.10790","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2309.10790","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2309.10790","pdf_url":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2309.10790","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.10790","pdf_url":"https://arxiv.org/pdf/2309.10790","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6399999856948853}],"awards":[{"id":"https://openalex.org/G1769687045","display_name":null,"funder_award_id":"2019-0-00075","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G2148870006","display_name":null,"funder_award_id":"2019-0-00075","funder_id":"https://openalex.org/F4320324161","funder_display_name":"Korea Advanced Institute of Science and Technology"},{"id":"https://openalex.org/G398188885","display_name":null,"funder_award_id":"2019-0-0007","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G4628738581","display_name":null,"funder_award_id":"No. 2019-0-00075","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"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/G5415505637","display_name":null,"funder_award_id":"2019-0-00075","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320322035","display_name":"Rural Development Administration","ror":"https://ror.org/03xs9yg50"},{"id":"https://openalex.org/F4320324161","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63"},{"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":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4386908259.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2778153218","https://openalex.org/W1531601525","https://openalex.org/W1950940422","https://openalex.org/W4283822356","https://openalex.org/W2129146436","https://openalex.org/W2032507829","https://openalex.org/W2147282173"],"abstract_inverted_index":{"Developing":[0],"an":[1,23],"agent":[2],"capable":[3],"of":[4,125],"adapting":[5],"to":[6,27,46,117],"unseen":[7,113],"environments":[8],"remains":[9],"a":[10,48,70,76,130],"difficult":[11],"challenge":[12],"in":[13,57,105],"imitation":[14],"learning.":[15],"This":[16,103],"work":[17],"presents":[18],"Adaptive":[19],"Return-conditioned":[20],"Policy":[21],"(ARP),":[22],"efficient":[24],"framework":[25],"designed":[26],"enhance":[28],"the":[29,58,87,100,123,139,149],"agent's":[30],"generalization":[31,107],"ability":[32],"using":[33,79],"natural":[34,54],"language":[35,55],"task":[36],"descriptions":[37],"and":[38,53,66,143],"pre-trained":[39,59,134],"multimodal":[40,60,84,88,135],"encoders.":[41],"Our":[42],"key":[43],"idea":[44],"is":[45],"calculate":[47],"similarity":[49],"between":[50],"visual":[51],"observations":[52],"instructions":[56],"embedding":[61],"space":[62],"(such":[63],"as":[64,69],"CLIP)":[65],"use":[67],"it":[68],"reward":[71],"signal.":[72],"We":[73],"then":[74],"train":[75],"return-conditioned":[77],"policy":[78],"expert":[80],"demonstrations":[81,142],"labeled":[82],"with":[83,112],"rewards.":[85],"Because":[86],"rewards":[89],"provide":[90],"adaptive":[91],"signals":[92],"at":[93],"each":[94],"timestep,":[95],"our":[96],"ARP":[97],"effectively":[98],"mitigates":[99],"goal":[101],"misgeneralization.":[102],"results":[104],"superior":[106],"performances":[108],"even":[109],"when":[110],"faced":[111],"text":[114],"instructions,":[115],"compared":[116],"existing":[118],"text-conditioned":[119],"policies.":[120],"To":[121],"improve":[122],"quality":[124],"rewards,":[126],"we":[127],"also":[128],"introduce":[129],"fine-tuning":[131],"method":[132],"for":[133],"encoders,":[136],"further":[137],"enhancing":[138],"performance.":[140],"Video":[141],"source":[144],"code":[145],"are":[146],"available":[147],"on":[148],"project":[150],"website:":[151],"\\url{https://sites.google.com/view/2023arp}.":[152]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}