{"id":"https://openalex.org/W4396880950","doi":"https://doi.org/10.24963/ijcai.2024/430","title":"A Conservative Approach for Few-Shot Transfer in Off-Dynamics Reinforcement Learning","display_name":"A Conservative Approach for Few-Shot Transfer in Off-Dynamics Reinforcement Learning","publication_year":2024,"publication_date":"2024-07-26","ids":{"openalex":"https://openalex.org/W4396880950","doi":"https://doi.org/10.24963/ijcai.2024/430"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2024/430","doi":"https://doi.org/10.24963/ijcai.2024/430","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2024/430","pdf_url":"https://www.ijcai.org/proceedings/2024/0430.pdf","source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2024/0430.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Paul Daoudi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Paul Daoudi","raw_affiliation_strings":["Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083387069","display_name":"Christophe Prieur","orcid":"https://orcid.org/0000-0002-4456-2019","observed_orcids":["https://orcid.org/0000-0002-4456-2019"]},"institutions":[{"id":"https://openalex.org/I2800493309","display_name":"Grain Inspection, Packers and Stockyards Administration","ror":"https://ror.org/056mcm922","country_code":"US","type":"government","lineage":["https://openalex.org/I1336096307","https://openalex.org/I2800493309"]},{"id":"https://openalex.org/I4210124956","display_name":"GIPSA-Lab","ror":"https://ror.org/02wrme198","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210124956","https://openalex.org/I899635006"]}],"countries":["FR","US"],"is_corresponding":false,"raw_author_name":"Christophe Prieur","raw_affiliation_strings":["GIPSA Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GIPSA Lab","institution_ids":["https://openalex.org/I2800493309","https://openalex.org/I4210124956"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066843673","display_name":"Bogdan Robu","orcid":"https://orcid.org/0000-0001-7568-007X","observed_orcids":["https://orcid.org/0000-0001-7568-007X"]},"institutions":[{"id":"https://openalex.org/I2800493309","display_name":"Grain Inspection, Packers and Stockyards Administration","ror":"https://ror.org/056mcm922","country_code":"US","type":"government","lineage":["https://openalex.org/I1336096307","https://openalex.org/I2800493309"]},{"id":"https://openalex.org/I4210124956","display_name":"GIPSA-Lab","ror":"https://ror.org/02wrme198","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210124956","https://openalex.org/I899635006"]}],"countries":["FR","US"],"is_corresponding":false,"raw_author_name":"Bogdan Robu","raw_affiliation_strings":["GIPSA Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GIPSA Lab","institution_ids":["https://openalex.org/I2800493309","https://openalex.org/I4210124956"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044958229","display_name":"Merwan Barlier","orcid":"https://orcid.org/0000-0001-7545-526X","observed_orcids":["https://orcid.org/0000-0001-7545-526X"]},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Merwan Barlier","raw_affiliation_strings":["Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011094173","display_name":"Ludovic Dos Santos","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210161401","display_name":"Criteo (France)","ror":"https://ror.org/04vyg0r47","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210161401"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ludovic Dos Santos","raw_affiliation_strings":["Criteo AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Criteo AI Lab","institution_ids":["https://openalex.org/I4210161401"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3157,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.52732911,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3890","last_page":"3898"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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":0.00019999999494757503,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/few-shot-transfer","display_name":"few-shot transfer","score":0.9259999990463257},{"id":"https://openalex.org/keywords/imitation-learning","display_name":"imitation learning","score":0.6740000247955322},{"id":"https://openalex.org/keywords/policy-transfer","display_name":"policy transfer","score":0.5889999866485596},{"id":"https://openalex.org/keywords/high-dimensional-systems","display_name":"high-dimensional systems","score":0.6179999709129333}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7347666025161743},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.651588499546051},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.618883490562439},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5892192125320435},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5402401089668274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4524567723274231},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13175755739212036},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.10774862766265869},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.06229415535926819},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.24963/ijcai.2024/430","doi":"https://doi.org/10.24963/ijcai.2024/430","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2024/430","pdf_url":"https://www.ijcai.org/proceedings/2024/0430.pdf","source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2312.15474","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.15474","pdf_url":"https://arxiv.org/pdf/2312.15474","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":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-04574316v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-04574316","pdf_url":"https://hal.science/hal-04574316v1/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IJCAI 2024 - International Joint Conference on Artificial Intelligence, Aug 2024, Jeju Island, South Korea","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2312.15474","doi":"https://doi.org/10.48550/arxiv.2312.15474","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2312.15474","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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2024/430","doi":"https://doi.org/10.24963/ijcai.2024/430","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2024/430","pdf_url":"https://www.ijcai.org/proceedings/2024/0430.pdf","source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396880950.pdf","grobid_xml":"https://content.openalex.org/works/W4396880950.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W2736601468","https://openalex.org/W2966684444","https://openalex.org/W3037207827"],"related_works":["https://openalex.org/W4415797516","https://openalex.org/W4405785031","https://openalex.org/W4407693160","https://openalex.org/W7124286787","https://openalex.org/W4415800597","https://openalex.org/W4417256833","https://openalex.org/W4395661562","https://openalex.org/W7133211669","https://openalex.org/W7125957354","https://openalex.org/W4409479689"],"abstract_inverted_index":{"Off-dynamics":[0],"Reinforcement":[1],"Learning":[2,94],"(ODRL)":[3],"seeks":[4],"to":[5,13,51,74,104,126,139,153],"transfer":[6],"a":[7,10,14,63,76,102],"policy":[8],"from":[9,68],"source":[11,36],"environment":[12,16,48,71,129],"target":[15,57,70,128],"characterized":[17],"by":[18,89,109],"distinct":[19],"yet":[20],"similar":[21],"dynamics.":[22],"In":[23,59],"this":[24,47,81],"context,":[25],"traditional":[26],"RL":[27,97],"agents":[28],"depend":[29],"excessively":[30],"on":[31],"the":[32,35,40,56,60,69,106,110,127],"dynamics":[33],"of":[34,42,66],"environment,":[37],"resulting":[38],"in":[39,46,55,92],"discovery":[41],"policies":[43],"that":[44],"excel":[45],"but":[49],"fail":[50],"provide":[52],"reasonable":[53],"performance":[54,150],"one.":[58],"few-shot":[61],"framework,":[62],"limited":[64],"number":[65],"transitions":[67],"are":[72],"introduced":[73],"facilitate":[75],"more":[77],"effective":[78],"transfer.":[79],"Addressing":[80],"challenge,":[82],"we":[83],"propose":[84],"an":[85],"innovative":[86],"approach":[87],"inspired":[88],"recent":[90],"advancements":[91],"Imitation":[93],"and":[95],"Conservative":[96],"algorithms.":[98],"This":[99],"method":[100,116,148],"introduces":[101],"penalty":[103],"regulate":[105],"trajectories":[107],"generated":[108],"source-trained":[111],"policy.":[112],"We":[113],"evaluate":[114],"our":[115,146],"across":[117],"various":[118],"environments":[119],"representing":[120],"diverse":[121],"off-dynamics":[122],"conditions,":[123],"where":[124],"access":[125],"is":[130],"extremely":[131],"limited.":[132],"These":[133],"experiments":[134],"include":[135],"high-dimensional":[136],"systems":[137],"relevant":[138],"real-world":[140],"applications.":[141],"Across":[142],"most":[143],"tested":[144],"scenarios,":[145],"proposed":[147],"demonstrates":[149],"improvements":[151],"compared":[152],"existing":[154],"baselines.":[155]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-05-14T00:00:00"}