{"id":"https://openalex.org/W3204432076","doi":"https://doi.org/10.48550/arxiv.2112.06424","title":"A Benchmark for Low-Switching-Cost Reinforcement Learning","display_name":"A Benchmark for Low-Switching-Cost Reinforcement Learning","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W3204432076","doi":"https://doi.org/10.48550/arxiv.2112.06424","mag":"3204432076"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2112.06424","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2112.06424","pdf_url":"https://arxiv.org/pdf/2112.06424","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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2112.06424","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014274752","display_name":"Shusheng Xu","orcid":"https://orcid.org/0000-0002-6016-6112","observed_orcids":["https://orcid.org/0000-0002-6016-6112"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Shusheng","raw_affiliation_strings":["IIIS , Tsinghua Unveristy , Beijing ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIS , Tsinghua Unveristy , Beijing ,","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036275688","display_name":"Yancheng Liang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang, Yancheng","raw_affiliation_strings":["IIIS , Tsinghua Unveristy , Beijing ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIS , Tsinghua Unveristy , Beijing ,","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100461870","display_name":"Yunfei Li","orcid":"https://orcid.org/0000-0003-1734-5008","observed_orcids":["https://orcid.org/0000-0003-1734-5008"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Yunfei","raw_affiliation_strings":["IIIS , Tsinghua Unveristy , Beijing ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIS , Tsinghua Unveristy , Beijing ,","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033061754","display_name":"Simon S. Du","orcid":"https://orcid.org/0000-0003-0056-8299","observed_orcids":["https://orcid.org/0000-0003-0056-8299"]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Du, Simon Shaolei","raw_affiliation_strings":["University of Washington ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington ,","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073986426","display_name":"Yi Wu","orcid":"https://orcid.org/0009-0006-3120-3769","observed_orcids":["https://orcid.org/0009-0006-3120-3769"]},"institutions":[{"id":"https://openalex.org/I4405259049","display_name":"Shanghai Qi Zhi Institute","ror":"https://ror.org/01n14yn69","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4405259049"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu, Yi","raw_affiliation_strings":["IIIS , Tsinghua Unveristy , Beijing ,","Shanghai Qi Zhi institute , Shanghai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIS , Tsinghua Unveristy , Beijing ,","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shanghai Qi Zhi institute , Shanghai","institution_ids":["https://openalex.org/I4405259049"]}]}],"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":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":9.999999747378752e-05,"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/policy-switching","display_name":"policy switching","score":0.9039999842643738},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.7360000014305115},{"id":"https://openalex.org/keywords/sample-efficiency","display_name":"sample efficiency","score":0.7360000014305115},{"id":"https://openalex.org/keywords/atari-games","display_name":"Atari games","score":0.8669999837875366},{"id":"https://openalex.org/keywords/robot-control","display_name":"robot control","score":0.9829999804496765}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8862199783325195},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8554161190986633},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7657699584960938},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47323569655418396},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.45781320333480835},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4352204203605652},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.41029611229896545},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34728676080703735},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08731099963188171},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2112.06424","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2112.06424","pdf_url":"https://arxiv.org/pdf/2112.06424","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":"doi:10.48550/arxiv.2112.06424","doi":"https://doi.org/10.48550/arxiv.2112.06424","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2112.06424","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2112.06424","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2112.06424","pdf_url":"https://arxiv.org/pdf/2112.06424","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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4226105937","https://openalex.org/W3133369317","https://openalex.org/W4322616362","https://openalex.org/W4320342428","https://openalex.org/W4400373872","https://openalex.org/W4416132759","https://openalex.org/W3119494765","https://openalex.org/W7133242746","https://openalex.org/W4415796359","https://openalex.org/W4221164275"],"abstract_inverted_index":{"A":[0],"ubiquitous":[1],"requirement":[2],"in":[3,81,179],"many":[4],"practical":[5],"reinforcement":[6],"learning":[7],"(RL)":[8],"applications,":[9],"including":[10,97],"medical":[11,111],"treatment,":[12],"recommendation":[13],"system,":[14],"education":[15],"and":[16,103,117,130,176],"robotics,":[17],"is":[18,36],"that":[19,23],"the":[20,27,42,47,55,74,114,123,138,148,151],"deployed":[21],"policy":[22,50],"actually":[24],"interacts":[25],"with":[26,68],"environment":[28],"cannot":[29],"change":[30],"frequently.":[31],"Such":[32],"an":[33],"RL":[34,66,83,129,170],"setting":[35],"called":[37],"low-switching-cost":[38,128,152,169],"RL,":[39],"i.e.,":[40],"achieving":[41],"highest":[43],"reward":[44],"while":[45,141],"reducing":[46],"number":[48],"of":[49,58,73,94],"switches":[51],"during":[52],"training.":[53],"Despite":[54],"recent":[56],"trend":[57],"theoretical":[59],"studies":[60],"aiming":[61],"to":[62,136,147],"design":[63],"provably":[64],"efficient":[65],"algorithms":[67],"low":[69],"switching":[70,139],"costs,":[71],"none":[72],"existing":[75],"approaches":[76],"have":[77],"been":[78],"thoroughly":[79],"evaluated":[80],"popular":[82],"testbeds.":[84],"In":[85],"this":[86,156],"paper,":[87],"we":[88,121],"systematically":[89],"studied":[90],"a":[91,110,143,161],"wide":[92],"collection":[93],"policy-switching":[95],"approaches,":[96],"theoretically":[98],"guided":[99],"criteria,":[100],"policy-difference-based":[101],"methods,":[102],"non-adaptive":[104],"baselines.":[105],"Through":[106],"extensive":[107],"experiments":[108],"on":[109,134],"treatment":[112],"environment,":[113],"Atari":[115],"games,":[116],"robotic":[118],"control":[119],"tasks,":[120],"present":[122],"first":[124],"empirical":[125],"benchmark":[126,157],"for":[127,164],"report":[131],"novel":[132],"findings":[133],"how":[135],"decrease":[137],"cost":[140],"maintain":[142],"similar":[144],"sample":[145],"efficiency":[146],"case":[149],"without":[150],"constraint.":[153],"We":[154,172],"hope":[155],"could":[158],"serve":[159],"as":[160],"starting":[162],"point":[163],"developing":[165],"more":[166],"practically":[167],"effective":[168],"algorithms.":[171],"release":[173],"our":[174],"code":[175],"complete":[177],"results":[178],"https://sites.google.com/view/low-switching-cost-rl.":[180]},"counts_by_year":[],"updated_date":"2026-10-02T10:15:12.560889","created_date":"2021-10-11T00:00:00"}