{"id":"https://openalex.org/W7135013746","doi":"https://doi.org/10.48550/arxiv.2603.10545","title":"Learning to Score: Tuning Cluster Schedulers through Reinforcement Learning","display_name":"Learning to Score: Tuning Cluster Schedulers through Reinforcement Learning","publication_year":2026,"publication_date":"2026-03-11","ids":{"openalex":"https://openalex.org/W7135013746","doi":"https://doi.org/10.48550/arxiv.2603.10545"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.10545","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.10545","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.10545","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004304345","display_name":"Martin Asenov","orcid":"https://orcid.org/0000-0003-4610-3112"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Asenov, Martin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128812894","display_name":"Qiwen Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deng, Qiwen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020484928","display_name":"Gingfung Yeung","orcid":"https://orcid.org/0000-0002-3845-0686"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yeung, Gingfung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5057205845","display_name":"Adam Barker","orcid":"https://orcid.org/0000-0002-0463-7207"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Barker, Adam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.6820999979972839,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.6820999979972839,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.21080000698566437,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.0272000003606081,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.7347999811172485},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.6657000184059143},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5852000117301941},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.5001000165939331},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43959999084472656},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4392000138759613},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.42089998722076416},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.41600000858306885}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7347999811172485},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7318999767303467},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.6657000184059143},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5852000117301941},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5378999710083008},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5073000192642212},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5001000165939331},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43959999084472656},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4392000138759613},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.42089998722076416},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.41600000858306885},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.4065999984741211},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.3840000033378601},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3587999939918518},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3102000057697296},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.2614000141620636}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.10545","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.10545","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.10545","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.10545","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.6563226580619812,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Efficiently":[0],"allocating":[1],"incoming":[2,25],"jobs":[3,109],"to":[4,11,23,37,53,133,190,196],"nodes":[5],"in":[6,14,95,161,200],"large-scale":[7],"clusters":[8,163],"can":[9],"lead":[10,52],"substantial":[12],"improvements":[13],"both":[15],"cluster":[16,27,176],"utilization":[17],"and":[18,80,123,158,164,175,193],"job":[19],"performance.":[20],"In":[21],"order":[22],"allocate":[24],"jobs,":[26],"schedulers":[28],"usually":[29,47],"rely":[30],"on":[31,118,170,185],"a":[32,87,111,129,201],"set":[33],"of":[34,67,73,103,108,137,143,173],"scoring":[35,44,74,97],"functions":[36,45],"rank":[38],"feasible":[39],"nodes.":[40],"Results":[41],"from":[42],"individual":[43],"are":[46],"weighted":[48],"equally,":[49],"which":[50],"could":[51],"sub-optimal":[54],"deployments":[55],"as":[56],"the":[57,65,71,93,100,105,135,180,197],"one-size-fits-all":[58],"solution":[59],"does":[60],"not":[61],"take":[62],"into":[63],"account":[64],"characteristics":[66],"each":[68],"workload.":[69],"Tuning":[70],"weights":[72,94,192],"functions,":[75],"however,":[76],"requires":[77],"expert":[78],"knowledge":[79],"is":[81,116,168],"computationally":[82],"expensive.":[83],"This":[84],"paper":[85],"proposes":[86],"reinforcement":[88],"learning":[89,92],"approach":[90,115,182],"for":[91,110,146],"scheduler":[96],"algorithms":[98],"with":[99],"overall":[101],"objective":[102,136],"improving":[104],"end-to-end":[106],"performance":[107,160,184],"given":[112],"cluster.":[113],"Our":[114],"based":[117],"percentage":[119,130],"improvement":[120,131],"reward,":[121],"frame-stacking,":[122],"limiting":[124],"domain":[125,154],"information.":[126],"We":[127,178],"propose":[128],"reward":[132],"address":[134],"multi-step":[138],"parameter":[139],"tuning.":[140],"The":[141,166],"inclusion":[142],"frame-stacking":[144],"allows":[145],"carrying":[147],"information":[148,155],"across":[149],"an":[150],"optimization":[151],"experiment.":[152],"Limiting":[153],"prevents":[156],"overfitting":[157],"improves":[159,183],"unseen":[162],"workloads.":[165],"policy":[167],"trained":[169],"different":[171],"combinations":[172],"workloads":[174],"setups.":[177],"demonstrate":[179],"proposed":[181],"average":[186],"by":[187],"33\\%":[188],"compared":[189,195],"fixed":[191],"12\\%":[194],"best-performing":[198],"baseline":[199],"lab-based":[202],"serverless":[203],"scenario.":[204]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-13T00:00:00"}