{"id":"https://openalex.org/W4386815404","doi":"https://doi.org/10.14428/esann/2023.es2023-117","title":"A model-based approach to meta-Reinforcement Learning: Transformers and tree search","display_name":"A model-based approach to meta-Reinforcement Learning: Transformers and tree search","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386815404","doi":"https://doi.org/10.14428/esann/2023.es2023-117"},"language":"en","primary_location":{"id":"doi:10.14428/esann/2023.es2023-117","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2023.es2023-117","pdf_url":"http://dx.doi.org/10.14428/esann/2023.es2023-117","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2023 proceesdings","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dx.doi.org/10.14428/esann/2023.es2023-117","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043473570","display_name":"Brieuc Pinon","orcid":"https://orcid.org/0000-0001-5727-932X"},"institutions":[{"id":"https://openalex.org/I95674353","display_name":"UCLouvain","ror":"https://ror.org/02495e989","country_code":"BE","type":"education","lineage":["https://openalex.org/I95674353"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Brieuc Pinon","raw_affiliation_strings":["UCLouvain , Department of Mathematical engineering Louvain-la-Neuve -Belgium","UCLouvain, Department of Mathematical engineering Louvain-la-Neuve -Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCLouvain , Department of Mathematical engineering Louvain-la-Neuve -Belgium","institution_ids":["https://openalex.org/I95674353"]},{"raw_affiliation_string":"UCLouvain, Department of Mathematical engineering Louvain-la-Neuve -Belgium","institution_ids":["https://openalex.org/I95674353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056625594","display_name":"Rapha\u00ebl M. Jungers","orcid":"https://orcid.org/0000-0002-7789-0940"},"institutions":[{"id":"https://openalex.org/I95674353","display_name":"UCLouvain","ror":"https://ror.org/02495e989","country_code":"BE","type":"education","lineage":["https://openalex.org/I95674353"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Rapha\u00ebl Jungers","raw_affiliation_strings":["UCLouvain , Department of Mathematical engineering Louvain-la-Neuve -Belgium","UCLouvain, Department of Mathematical engineering Louvain-la-Neuve -Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCLouvain , Department of Mathematical engineering Louvain-la-Neuve -Belgium","institution_ids":["https://openalex.org/I95674353"]},{"raw_affiliation_string":"UCLouvain, Department of Mathematical engineering Louvain-la-Neuve -Belgium","institution_ids":["https://openalex.org/I95674353"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006354562","display_name":"Jean\u2010Charles Delvenne","orcid":"https://orcid.org/0000-0003-2356-7790"},"institutions":[{"id":"https://openalex.org/I95674353","display_name":"UCLouvain","ror":"https://ror.org/02495e989","country_code":"BE","type":"education","lineage":["https://openalex.org/I95674353"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Jean-Charles Delvenne","raw_affiliation_strings":["UCLouvain , Department of Mathematical engineering Louvain-la-Neuve -Belgium","UCLouvain, Department of Mathematical engineering Louvain-la-Neuve -Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCLouvain , Department of Mathematical engineering Louvain-la-Neuve -Belgium","institution_ids":["https://openalex.org/I95674353"]},{"raw_affiliation_string":"UCLouvain, Department of Mathematical engineering Louvain-la-Neuve -Belgium","institution_ids":["https://openalex.org/I95674353"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I95674353"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"333","last_page":"338"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8799999952316284,"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":0.8799999952316284,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.8571000099182129,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7984554767608643},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6828664541244507},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5237253308296204},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5160045623779297},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4620570242404938},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44725823402404785},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.161711186170578},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1229393482208252},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.0707595944404602}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7984554767608643},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6828664541244507},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5237253308296204},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5160045623779297},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4620570242404938},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44725823402404785},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.161711186170578},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1229393482208252},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0707595944404602},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14428/esann/2023.es2023-117","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2023.es2023-117","pdf_url":"http://dx.doi.org/10.14428/esann/2023.es2023-117","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2023 proceesdings","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.14428/esann/2023.es2023-117","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2023.es2023-117","pdf_url":"http://dx.doi.org/10.14428/esann/2023.es2023-117","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2023 proceesdings","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321390","display_name":"Fonds De La Recherche Scientifique - FNRS","ror":"https://ror.org/03q83t159"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386815404.pdf","grobid_xml":"https://content.openalex.org/works/W4386815404.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2257979135","https://openalex.org/W2578206533","https://openalex.org/W2980433389","https://openalex.org/W3163842339","https://openalex.org/W3206344027","https://openalex.org/W4287332184","https://openalex.org/W4300971732"],"related_works":["https://openalex.org/W3074294383","https://openalex.org/W4206669594","https://openalex.org/W2961085424","https://openalex.org/W2959276766","https://openalex.org/W4295941380","https://openalex.org/W260766989","https://openalex.org/W3139193008","https://openalex.org/W4306674287","https://openalex.org/W3111983280","https://openalex.org/W4319083788"],"abstract_inverted_index":{"Meta-learning":[0],"is":[1,64,90],"a":[2,29,41,58,81,85,91,111],"line":[3],"of":[4,22,43,130],"research":[5],"that":[6,34,63],"develops":[7],"the":[8,20,96,107,122,128],"ability":[9],"to":[10,14,31,53,73,75,94,136],"leverage":[11],"past":[12],"experiences":[13],"efficiently":[15,35],"solve":[16],"new":[17],"learning":[18],"problems.In":[19],"context":[21],"Reinforcement":[23],"Learning":[24],"(RL),":[25],"meta-RL":[26],"methods":[27,71,120],"demonstrate":[28],"capability":[30],"learn":[32,74],"behaviors":[33],"acquire":[36],"and":[37,139],"exploit":[38],"information":[39],"on":[40,121],"set":[42],"related":[44],"tasks.The":[45],"Alchemy":[46,98,124],"benchmark":[47],"has":[48],"been":[49],"proposed":[50],"in":[51,142],"[1]":[52],"test":[54],"such":[55],"methods.Alchemy":[56],"features":[57],"rich":[59],"structured":[60],"latent":[61],"space":[62],"challenging":[65],"for":[66],"state-of-the-art":[67],"model-free":[68],"RL":[69],"methods.These":[70],"fail":[72],"properly":[76],"explore":[77],"then":[78],"exploit.We":[79],"develop":[80],"model-based":[82,131],"algorithm.We":[83],"train":[84],"model":[86,109],"whose":[87],"principal":[88],"block":[89],"Transformer":[92],"Decoder":[93],"fit":[95],"symbolic":[97,123],"environment":[99],"dynamics.Then":[100],"we":[101],"define":[102],"an":[103],"online":[104,134],"planner":[105],"with":[106,133],"learned":[108],"using":[110],"tree":[112],"search":[113],"method.This":[114],"algorithm":[115],"significantly":[116],"outperforms":[117],"previously":[118],"applied":[119],"problem.Our":[125],"results":[126],"reveal":[127],"relevance":[129],"approaches":[132],"planning":[135],"perform":[137],"exploration":[138],"exploitation":[140],"successfully":[141],"meta-RL.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-20T07:56:41.581041","created_date":"2025-10-10T00:00:00"}