{"id":"https://openalex.org/W4403799481","doi":"https://doi.org/10.48550/arxiv.2409.18827","title":"ARLBench: Flexible and Efficient Benchmarking for Hyperparameter Optimization in Reinforcement Learning","display_name":"ARLBench: Flexible and Efficient Benchmarking for Hyperparameter Optimization in Reinforcement Learning","publication_year":2024,"publication_date":"2024-09-27","ids":{"openalex":"https://openalex.org/W4403799481","doi":"https://doi.org/10.48550/arxiv.2409.18827"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2409.18827","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.18827","pdf_url":"https://arxiv.org/pdf/2409.18827","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/2409.18827","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114420289","display_name":"Jannis Becktepe","orcid":"https://orcid.org/0009-0008-5009-390X","observed_orcids":["https://orcid.org/0009-0008-5009-390X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Becktepe, Jannis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Dierkes, Julian","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dierkes, Julian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035141000","display_name":"Carolin Benjamins","orcid":"https://orcid.org/0009-0007-4643-3564","observed_orcids":["https://orcid.org/0009-0007-4643-3564"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Benjamins, Carolin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102919894","display_name":"Aditya Mohan","orcid":"https://orcid.org/0000-0003-0092-3780","observed_orcids":["https://orcid.org/0000-0003-0092-3780"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohan, Aditya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078696011","display_name":"David Salinas","orcid":"https://orcid.org/0000-0002-8980-4018","observed_orcids":["https://orcid.org/0000-0002-8980-4018"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Salinas, David","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Rajan, Raghu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rajan, Raghu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031002895","display_name":"Frank Hutter","orcid":"https://orcid.org/0000-0002-2037-3694","observed_orcids":["https://orcid.org/0000-0002-2037-3694"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hutter, Frank","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025342513","display_name":"Holger H. Hoos","orcid":"https://orcid.org/0000-0003-0629-0099","observed_orcids":["https://orcid.org/0000-0003-0629-0099"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hoos, Holger","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045511267","display_name":"Marius Lindauer","orcid":"https://orcid.org/0000-0002-9675-3175","observed_orcids":["https://orcid.org/0000-0002-9675-3175"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lindauer, Marius","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038833033","display_name":"Theresa Eimer","orcid":"https://orcid.org/0000-0001-5561-5908","observed_orcids":["https://orcid.org/0000-0001-5561-5908"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eimer, Theresa","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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7914999723434448,"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":0.7914999723434448,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.18790000677108765,"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":0.005200000014156103,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hyperparameter-optimization","display_name":"hyperparameter optimization","score":0.9620000123977661},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.9700000286102295},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.6769999861717224},{"id":"https://openalex.org/keywords/performance-profiles","display_name":"performance profiles","score":0.5600000023841858}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.894971489906311},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.8573331832885742},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7548094987869263},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5462384819984436},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5139498114585876},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5076617002487183},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.46762970089912415},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.33630019426345825},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.32209312915802},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.13501626253128052},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.1227792501449585},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.05743977427482605}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2409.18827","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.18827","pdf_url":"https://arxiv.org/pdf/2409.18827","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:freidok.uni-freiburg.de:262194","doi":null,"is_oa":false,"landing_page_url":"https://freidok.uni-freiburg.de/data/262194","pdf_url":null,"source":{"id":"https://openalex.org/S4306401057","display_name":"FreiDok plus (Universit\u00e4tsbibliothek Freiburg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I161046081","host_organization_name":"University of Freiburg","host_organization_lineage":["https://openalex.org/I161046081"],"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":"preprint"},{"id":"doi:10.48550/arxiv.2409.18827","doi":"https://doi.org/10.48550/arxiv.2409.18827","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2409.18827","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2409.18827","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.18827","pdf_url":"https://arxiv.org/pdf/2409.18827","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"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/W4379473886","https://openalex.org/W4362679487","https://openalex.org/W7208742757","https://openalex.org/W6958846956","https://openalex.org/W4226515712","https://openalex.org/W3175536591","https://openalex.org/W7171851580","https://openalex.org/W2954882791","https://openalex.org/W4416545271","https://openalex.org/W3082857813"],"abstract_inverted_index":{"Hyperparameters":[0],"are":[1,33,174],"a":[2,29,38,55,92,99,111,122,130],"critical":[3],"factor":[4],"in":[5,61,74,81,84,139],"reliably":[6],"training":[7],"well-performing":[8],"reinforcement":[9],"learning":[10],"(RL)":[11],"agents.":[12],"Unfortunately,":[13],"developing":[14],"and":[15,26,46,103,144,161,171],"evaluating":[16],"automated":[17,116],"approaches":[18,32,69],"for":[19,57,109,164],"tuning":[20],"such":[21,31],"hyperparameters":[22],"is":[23,153,157],"both":[24],"costly":[25],"time-consuming.":[27],"As":[28],"result,":[30],"often":[34],"only":[35,121],"evaluated":[36],"on":[37,137,147,166],"single":[39],"domain":[40],"or":[41],"algorithm,":[42],"making":[43],"comparisons":[44,65],"difficult":[45],"limiting":[47],"insights":[48],"into":[49,79],"their":[50],"generalizability.":[51],"We":[52],"propose":[53],"ARLBench,":[54],"benchmark":[56,170],"hyperparameter":[58,148],"optimization":[59],"(HPO)":[60],"RL":[62,117],"that":[63,150],"allows":[64,108],"of":[66,95,101,114,124,133],"diverse":[67],"HPO":[68,80,96,138],"while":[70],"being":[71],"highly":[72],"efficient":[73],"evaluation.":[75],"To":[76],"enable":[77],"research":[78,165],"RL,":[82],"even":[83],"settings":[85],"with":[86],"low":[87],"compute":[88,126],"resources,":[89],"we":[90],"select":[91],"representative":[93],"subset":[94],"tasks":[97],"spanning":[98],"variety":[100],"algorithm":[102],"environment":[104],"combinations.":[105],"This":[106],"selection":[107,152],"generating":[110],"performance":[112],"profile":[113],"an":[115,158],"(AutoRL)":[118],"method":[119],"using":[120],"fraction":[123],"the":[125,142,169,172],"previously":[127],"necessary,":[128],"enabling":[129],"broader":[131],"range":[132],"researchers":[134],"to":[135],"work":[136],"RL.":[140],"With":[141],"extensive":[143],"large-scale":[145],"dataset":[146,173],"landscapes":[149],"our":[151],"based":[154],"on,":[155],"ARLBench":[156],"efficient,":[159],"flexible,":[160],"future-oriented":[162],"foundation":[163],"AutoRL.":[167],"Both":[168],"available":[175],"at":[176],"https://github.com/automl/arlbench.":[177]},"counts_by_year":[],"updated_date":"2026-09-29T14:09:16.559479","created_date":"2024-10-27T00:00:00"}