{"id":"https://openalex.org/W4362600435","doi":"https://doi.org/10.5555/3545946.3598718","title":"Enhancing Reinforcement Learning Agents with Local Guides","display_name":"Enhancing Reinforcement Learning Agents with Local Guides","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4362600435","doi":"https://doi.org/10.5555/3545946.3598718"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2402.13930","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.13930","pdf_url":"https://arxiv.org/pdf/2402.13930","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,"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"},"type":"preprint","indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2402.13930","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036818441","display_name":"Paul Daoudi","orcid":null},"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":"Daoudi, Paul","raw_affiliation_strings":["Huawei Noah\u2019s Ark lab (China)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah\u2019s Ark lab (China)","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066843673","display_name":"Bogdan Robu","orcid":"https://orcid.org/0000-0001-7568-007X"},"institutions":[{"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","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Robu, Bogdan","raw_affiliation_strings":["GIPSA-MODUS - GIPSA - Modelling and Optimal Decision for Uncertain Systems (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX  - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GIPSA-MODUS - GIPSA - Modelling and Optimal Decision for Uncertain Systems (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX  - France)","institution_ids":["https://openalex.org/I4210124956"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083387069","display_name":"Christophe Prieur","orcid":"https://orcid.org/0000-0002-4456-2019"},"institutions":[{"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","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Prieur, Christophe","raw_affiliation_strings":["GIPSA-INFINITY - GIPSA - Infinite Dimensional Dynamics (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX  - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GIPSA-INFINITY - GIPSA - Infinite Dimensional Dynamics (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX  - France)","institution_ids":["https://openalex.org/I4210124956"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069806569","display_name":"Ludovic Dos Santos","orcid":null},"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":"Dos Santos, Ludovic","raw_affiliation_strings":["Criteo AI Lab (Paris - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Criteo AI Lab (Paris - France)","institution_ids":["https://openalex.org/I4210161401"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044958229","display_name":"Merwan Barlier","orcid":null},"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":"Barlier, Merwan","raw_affiliation_strings":["Huawei Noah\u2019s Ark lab (China)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah\u2019s Ark lab (China)","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.984000027179718,"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":0.984000027179718,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.954200029373169,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10142","display_name":"Formal Methods in Verification","score":0.9075000286102295,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9450271129608154},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7417925596237183},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5322442054748535},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.5059229731559753},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49746206402778625},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.46177613735198975},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4417310953140259},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.42736685276031494},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.4140360355377197},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40108585357666016},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1315506398677826},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09946319460868835}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9450271129608154},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7417925596237183},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5322442054748535},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.5059229731559753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49746206402778625},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.46177613735198975},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4417310953140259},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.42736685276031494},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.4140360355377197},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40108585357666016},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1315506398677826},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09946319460868835},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2402.13930","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.13930","pdf_url":"https://arxiv.org/pdf/2402.13930","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,"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-04052358v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04052358","pdf_url":"https://hal.science/hal-04052358/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"Proceedings AAMAS '23","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2402.13930","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.13930","pdf_url":"https://arxiv.org/pdf/2402.13930","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,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4362600435.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3148138296","https://openalex.org/W4294873804","https://openalex.org/W2352650970","https://openalex.org/W3127551068","https://openalex.org/W2808546214","https://openalex.org/W3203256658","https://openalex.org/W1882507001","https://openalex.org/W2367922714","https://openalex.org/W2152445738","https://openalex.org/W77396219"],"abstract_inverted_index":{"This":[0,38],"paper":[1],"addresses":[2],"the":[3,56,78,85,93,108],"problem":[4],"of":[5,69,87,110],"integrating":[6],"local":[7,57],"guide":[8],"policies":[9,105],"into":[10],"a":[11,29,34,42,51,67],"Reinforcement":[12,71,113],"Learning":[13,72,114],"agent.":[14],"For":[15],"this,":[16],"we":[17],"show":[18],"how":[19],"to":[20,24,49,99,106],"adapt":[21],"existing":[22],"algorithms":[23],"this":[25],"setting":[26],"before":[27],"introducing":[28],"novel":[30],"algorithm":[31],"based":[32],"on":[33,41,66],"noisy":[35],"policy-switching":[36],"procedure.":[37],"approach":[39],"builds":[40],"proper":[43],"Approximate":[44],"Policy":[45],"Evaluation":[46],"(APE)":[47],"scheme":[48],"provide":[50],"perturbation":[52],"that":[53],"carefully":[54],"leads":[55],"guides":[58],"towards":[59],"better":[60],"actions.":[61],"We":[62],"evaluated":[63],"our":[64,96],"method":[65],"set":[68],"classical":[70],"problems,":[73],"including":[74],"safety-critical":[75],"systems":[76],"where":[77],"agent":[79,97],"cannot":[80],"enter":[81],"some":[82],"areas":[83],"at":[84,102],"risk":[86],"triggering":[88],"catastrophic":[89],"consequences.":[90],"In":[91],"all":[92],"proposed":[94],"environments,":[95],"proved":[98],"be":[100],"efficient":[101],"leveraging":[103],"those":[104],"improve":[107],"performance":[109],"any":[111],"APE-based":[112],"algorithm,":[115],"especially":[116],"in":[117],"its":[118],"first":[119],"learning":[120],"stages.":[121]},"counts_by_year":[],"updated_date":"2026-08-08T01:25:22.217667","created_date":"2025-10-10T00:00:00"}