{"id":"https://openalex.org/W7124320709","doi":"https://doi.org/10.65109/xkdr2076","title":"Relaxed Exploration Constrained Reinforcement Learning","display_name":"Relaxed Exploration Constrained Reinforcement Learning","publication_year":2023,"publication_date":"2023-05-30","ids":{"openalex":"https://openalex.org/W7124320709","doi":"https://doi.org/10.65109/xkdr2076"},"language":"en","primary_location":{"id":"doi:10.65109/xkdr2076","doi":"https://doi.org/10.65109/xkdr2076","is_oa":false,"landing_page_url":"https://doi.org/10.65109/xkdr2076","pdf_url":null,"source":{"id":"https://openalex.org/S4306417597","display_name":"Adaptive Agents and Multi-Agents Systems","issn_l":"1548-8403","issn":["1548-8403"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"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":"International Joint Conference on Autonomous Agents and Multiagent Systems","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073638946","display_name":"Shahaf Shperberg","orcid":"https://orcid.org/0000-0001-7683-3031","observed_orcids":["https://orcid.org/0000-0001-7683-3031"]},"institutions":[{"id":"https://openalex.org/I124227911","display_name":"Ben-Gurion University of the Negev","ror":"https://ror.org/05tkyf982","country_code":"IL","type":"education","lineage":["https://openalex.org/I124227911"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Shahaf S. Shperberg","raw_affiliation_strings":["Ben-Gurion University, Be'er Sheva, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ben-Gurion University, Be'er Sheva, Israel","institution_ids":["https://openalex.org/I124227911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087217727","display_name":"Bo Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Liu","raw_affiliation_strings":["The University of Texas at Austin, Austin, UT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, UT, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001594330","display_name":"Peter Stone","orcid":"https://orcid.org/0000-0002-6795-420X","observed_orcids":["https://orcid.org/0000-0002-6795-420X"]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Stone","raw_affiliation_strings":["The University of Texas at Austin, Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4534,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.67602509,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2821","last_page":"2823"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/constrained-reinforcement-learning","display_name":"constrained reinforcement learning","score":0.9459999799728394},{"id":"https://openalex.org/keywords/constraint-relaxation","display_name":"constraint relaxation","score":0.6669999957084656},{"id":"https://openalex.org/keywords/curriculum-learning","display_name":"curriculum learning","score":0.890999972820282},{"id":"https://openalex.org/keywords/exploration","display_name":"exploration","score":0.6230000257492065},{"id":"https://openalex.org/keywords/policy-optimization","display_name":"policy optimization","score":0.5},{"id":"https://openalex.org/keywords/chloride-intracellular-channel","display_name":"CLIC","score":0.6579999923706055}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8561999797821045},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6656000018119812},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6449999809265137},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.44999998807907104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44029998779296875},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4092999994754791},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.39739999175071716},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.37450000643730164},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.3467999994754791},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.33000001311302185},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31209999322891235},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.29820001125335693},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.25690001249313354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.65109/xkdr2076","doi":"https://doi.org/10.65109/xkdr2076","is_oa":false,"landing_page_url":"https://doi.org/10.65109/xkdr2076","pdf_url":null,"source":{"id":"https://openalex.org/S4306417597","display_name":"Adaptive Agents and Multi-Agents Systems","issn_l":"1548-8403","issn":["1548-8403"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"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":"International Joint Conference on Autonomous Agents and Multiagent Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4390438207","https://openalex.org/W2002741962","https://openalex.org/W4385488495","https://openalex.org/W7103283561","https://openalex.org/W4403365237","https://openalex.org/W3211584761","https://openalex.org/W3180716444","https://openalex.org/W4378446801","https://openalex.org/W3189576409","https://openalex.org/W6979277852"],"abstract_inverted_index":{"This":[0],"extended":[1],"abstract":[2],"introduces":[3],"a":[4,31,39,95,123,140],"novel":[5],"setting":[6],"of":[7,41,130,157],"reinforcement":[8,23],"learning":[9,24],"with":[10,139],"constraints,":[11],"called":[12],"Relaxed":[13],"Exploration":[14],"Constrained":[15],"Reinforcement":[16],"Learning":[17],"(RECRL).":[18],"As":[19,86],"in":[20,44,52,75],"standard":[21],"constrained":[22],"(CRL),":[25],"the":[26,54,59,63,71,76,113,127,154],"aim":[27],"is":[28,47,69,73,79,150],"to":[29,38,81,90,104,108,119,122],"find":[30],"policy":[32,124],"that":[33,100,125,135],"maximizes":[34],"environmental":[35],"return":[36,142],"subject":[37],"set":[40,129,156],"constraints.":[42,85,131,158],"However,":[43],"RECRL":[45,91],"there":[46],"an":[48,87],"initial":[49,88],"training":[50,68,114,149],"phase":[51,115],"which":[53],"constraints":[55],"are":[56],"relaxed,":[57],"thus":[58],"agent":[60,72],"can":[61,101],"explore":[62],"environment":[64,77],"more":[65],"freely.":[66],"When":[67],"done,":[70],"deployed":[74],"and":[78],"required":[80],"fully":[82],"satisfy":[83],"all":[84],"approach":[89],"problems,":[92],"we":[93],"introduce":[94],"curriculum-based":[96],"approach,":[97],"named":[98],"CLiC,":[99],"be":[102],"applied":[103],"existing":[105],"CRL":[106],"algorithms":[107],"improve":[109],"their":[110],"exploration":[111],"during":[112,143],"while":[116],"allowing":[117],"them":[118],"gradually":[120],"converge":[121],"satisfies":[126],"full":[128],"Empirical":[132],"evaluation":[133],"shows":[134],"CLiC":[136],"produces":[137],"policies":[138,146],"higher":[141],"deployment":[144],"than":[145],"learned":[147],"when":[148],"done":[151],"using":[152],"only":[153],"strict":[155]},"counts_by_year":[{"year":2026,"cited_by_count":4}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-01-16T00:00:00"}