{"id":"https://openalex.org/W4402365084","doi":"https://doi.org/10.14428/esann/2024.es2024-181","title":"Vision Language Models as Policy Learners in Reinforcement Learning Environments","display_name":"Vision Language Models as Policy Learners in Reinforcement Learning Environments","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402365084","doi":"https://doi.org/10.14428/esann/2024.es2024-181"},"language":"en","primary_location":{"id":"doi:10.14428/esann/2024.es2024-181","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2024.es2024-181","pdf_url":"http://dx.doi.org/10.14428/esann/2024.es2024-181","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2024 proceesdings","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dx.doi.org/10.14428/esann/2024.es2024-181","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015514303","display_name":"Giovanni Bonetta","orcid":"https://orcid.org/0000-0003-4498-1026"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Giovanni Bonetta","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092803216","display_name":"Davide Zago","orcid":"https://orcid.org/0000-0003-1112-3543"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Davide Zago","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049044181","display_name":"R. Cancelliere","orcid":"https://orcid.org/0000-0002-9120-3799"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rossella Cancelliere","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009738158","display_name":"Mirko Polato","orcid":"https://orcid.org/0000-0003-4890-5020"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mirko Polato","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5066077296","display_name":"Bernardo Magnini","orcid":"https://orcid.org/0000-0002-0740-5778"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bernardo Magnini","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5015514303"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7343,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.7841423,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"503","last_page":"508"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13920","display_name":"Urban Planning and Valuation","score":0.13179999589920044,"subfield":{"id":"https://openalex.org/subfields/2308","display_name":"Management, Monitoring, Policy and Law"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13920","display_name":"Urban Planning and Valuation","score":0.13179999589920044,"subfield":{"id":"https://openalex.org/subfields/2308","display_name":"Management, Monitoring, Policy and Law"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12805","display_name":"Cognitive Science and Mapping","score":0.1152999997138977,"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":0.7196815013885498},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7058493494987488},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4222607910633087},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3596112132072449},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35539335012435913},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13669028878211975}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7196815013885498},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7058493494987488},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4222607910633087},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3596112132072449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35539335012435913},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13669028878211975},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14428/esann/2024.es2024-181","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2024.es2024-181","pdf_url":"http://dx.doi.org/10.14428/esann/2024.es2024-181","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2024 proceesdings","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.14428/esann/2024.es2024-181","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2024.es2024-181","pdf_url":"http://dx.doi.org/10.14428/esann/2024.es2024-181","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2024 proceesdings","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402365084.pdf","grobid_xml":"https://content.openalex.org/works/W4402365084.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588"],"abstract_inverted_index":{"In":[0],"various":[1],"domains":[2],"requiring":[3],"general":[4],"knowledge":[5,20,59],"and":[6,54,60,112,131,134,146,157],"agent":[7],"reasoning,":[8],"traditional":[9,117],"reinforcement":[10],"learning":[11],"(RL)":[12],"algorithms":[13],"often":[14],"start":[15],"from":[16],"scratch,":[17],"lacking":[18],"prior":[19],"of":[21,78,139],"the":[22,68,76,125],"environment.This":[23],"approach":[24],"can":[25],"lead":[26],"to":[27,67,116,124],"significant":[28],"inefficiencies":[29],"as":[30,89],"agents":[31],"sometimes":[32],"undergo":[33],"extensive":[34],"exploration":[35],"before":[36],"optimizing":[37],"their":[38],"actions.Conversely,":[39],"in":[40,72,106,155],"this":[41],"paper":[42,74],"we":[43,119,135,150],"assume":[44],"that":[45,103],"recent":[46],"Vision":[47],"Language":[48],"Models":[49],"(VLMs),":[50],"integrating":[51],"both":[52,143],"visual":[53,144],"textual":[55,147],"information,":[56],"possess":[57],"inherent":[58],"basic":[61],"reasoning":[62],"capabilities,":[63],"offering":[64],"potential":[65],"solutions":[66],"sample":[69],"inefficiency":[70],"problem":[71],"RL.The":[73],"explores":[75],"integration":[77],"VLMs":[79,105],"into":[80],"RL":[81,107,158],"by":[82],"employing":[83],"a":[84,90,121,137],"robust":[85],"VLM":[86,156],"model,":[87],"Idefics-9B,":[88],"policy":[91],"updated":[92],"via":[93],"Proximal":[94],"Policy":[95],"Optimization":[96],"(PPO).Experimental":[97],"results":[98],"on":[99],"simulated":[100],"environments":[101,141],"demonstrate":[102],"utilizing":[104],"significantly":[108],"accelerates":[109],"PPO":[110],"convergence":[111],"improves":[113],"rewards":[114],"compared":[115],"solutions.Additionally,":[118],"propose":[120],"streamlined":[122],"modification":[123],"model":[126],"architecture":[127],"for":[128],"memory":[129],"efficiency":[130],"lighter":[132],"training,":[133],"release":[136],"number":[138],"upgraded":[140],"featuring":[142],"observations":[145],"descriptions,":[148],"which,":[149],"hope,":[151],"will":[152],"facilitate":[153],"research":[154],"applications.Code":[159],"is":[160],"available":[161],"at:":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-11T06:11:40.159057","created_date":"2025-10-10T00:00:00"}