{"id":"https://openalex.org/W4410737485","doi":"https://doi.org/10.1109/lcsys.2025.3573943","title":"Generating Informative Benchmarks for Reinforcement Learning","display_name":"Generating Informative Benchmarks for Reinforcement Learning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4410737485","doi":"https://doi.org/10.1109/lcsys.2025.3573943"},"language":"en","primary_location":{"id":"doi:10.1109/lcsys.2025.3573943","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lcsys.2025.3573943","pdf_url":null,"source":{"id":"https://openalex.org/S4306422535","display_name":"IEEE Control Systems Letters","issn_l":"2475-1456","issn":["2475-1456"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Control Systems Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/lcsys.2025.3573943","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054781489","display_name":"Grigory Yaremenko","orcid":"https://orcid.org/0000-0002-8869-6422"},"institutions":[{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Grigory Yamerenko","raw_affiliation_strings":["Center for Digital Engineering, Skolkovo Institute of Science and Technology, Moscow, Russia","Skolkovo Institute of Science and Technology, Moscow, Russia"],"raw_orcid":"https://orcid.org/0000-0002-8869-6422","affiliations":[{"raw_affiliation_string":"Center for Digital Engineering, Skolkovo Institute of Science and Technology, Moscow, Russia","institution_ids":["https://openalex.org/I125989756"]},{"raw_affiliation_string":"Skolkovo Institute of Science and Technology, Moscow, Russia","institution_ids":["https://openalex.org/I125989756"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sinan Ibrahim","orcid":"https://orcid.org/0009-0006-9965-8209"},"institutions":[{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Sinan Ibrahim","raw_affiliation_strings":["Center for Digital Engineering, Skolkovo Institute of Science and Technology, Moscow, Russia","Skolkovo Institute of Science and Technology, Moscow, Russia"],"raw_orcid":"https://orcid.org/0009-0006-9965-8209","affiliations":[{"raw_affiliation_string":"Center for Digital Engineering, Skolkovo Institute of Science and Technology, Moscow, Russia","institution_ids":["https://openalex.org/I125989756"]},{"raw_affiliation_string":"Skolkovo Institute of Science and Technology, Moscow, Russia","institution_ids":["https://openalex.org/I125989756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073956671","display_name":"Francisco Moreno-Mora","orcid":"https://orcid.org/0000-0001-7732-9056"},"institutions":[{"id":"https://openalex.org/I2610724","display_name":"Chemnitz University of Technology","ror":"https://ror.org/00a208s56","country_code":"DE","type":"education","lineage":["https://openalex.org/I2610724"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Francisco Moreno-Mora","raw_affiliation_strings":["Automatic Control and System Dynamics Laboratory, Chemnitz University of Technology, Chemnitz, Germany","Chemnitz University of Technology, Cheminitz, Germany"],"raw_orcid":"https://orcid.org/0000-0001-7732-9056","affiliations":[{"raw_affiliation_string":"Automatic Control and System Dynamics Laboratory, Chemnitz University of Technology, Chemnitz, Germany","institution_ids":["https://openalex.org/I2610724"]},{"raw_affiliation_string":"Chemnitz University of Technology, Cheminitz, Germany","institution_ids":["https://openalex.org/I2610724"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065280230","display_name":"Pavel Osinenko","orcid":"https://orcid.org/0000-0002-6184-3293"},"institutions":[{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Pavel Osinenko","raw_affiliation_strings":["Center for Digital Engineering, Skolkovo Institute of Science and Technology, Moscow, Russia","Skolkovo Institute of Science and Technology, Moscow, Russia"],"raw_orcid":"https://orcid.org/0000-0002-6184-3293","affiliations":[{"raw_affiliation_string":"Center for Digital Engineering, Skolkovo Institute of Science and Technology, Moscow, Russia","institution_ids":["https://openalex.org/I125989756"]},{"raw_affiliation_string":"Skolkovo Institute of Science and Technology, Moscow, Russia","institution_ids":["https://openalex.org/I125989756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050202669","display_name":"Stefan Streif","orcid":"https://orcid.org/0000-0002-3398-1226"},"institutions":[{"id":"https://openalex.org/I2610724","display_name":"Chemnitz University of Technology","ror":"https://ror.org/00a208s56","country_code":"DE","type":"education","lineage":["https://openalex.org/I2610724"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Streif","raw_affiliation_strings":["Automatic Control and System Dynamics Laboratory, Chemnitz University of Technology, Chemnitz, Germany","Chemnitz University of Technology, Cheminitz, Germany"],"raw_orcid":"https://orcid.org/0000-0002-3398-1226","affiliations":[{"raw_affiliation_string":"Automatic Control and System Dynamics Laboratory, Chemnitz University of Technology, Chemnitz, Germany","institution_ids":["https://openalex.org/I2610724"]},{"raw_affiliation_string":"Chemnitz University of Technology, Cheminitz, Germany","institution_ids":["https://openalex.org/I2610724"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1294,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82883112,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"9","issue":null,"first_page":"480","last_page":"485"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.28360000252723694,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.28360000252723694,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7162092924118042},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6651079058647156},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5261282920837402},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4641951322555542},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3858588635921478},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.17910486459732056},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.06116372346878052}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7162092924118042},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6651079058647156},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5261282920837402},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4641951322555542},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3858588635921478},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.17910486459732056},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.06116372346878052}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lcsys.2025.3573943","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lcsys.2025.3573943","pdf_url":null,"source":{"id":"https://openalex.org/S4306422535","display_name":"IEEE Control Systems Letters","issn_l":"2475-1456","issn":["2475-1456"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Control Systems Letters","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/lcsys.2025.3573943","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lcsys.2025.3573943","pdf_url":null,"source":{"id":"https://openalex.org/S4306422535","display_name":"IEEE Control Systems Letters","issn_l":"2475-1456","issn":["2475-1456"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Control Systems Letters","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1650553268","https://openalex.org/W2092993939","https://openalex.org/W2754517384","https://openalex.org/W2974256297","https://openalex.org/W3037298378","https://openalex.org/W4379527413","https://openalex.org/W4381570256","https://openalex.org/W4401873149","https://openalex.org/W6767776290","https://openalex.org/W6775276923","https://openalex.org/W6787933629","https://openalex.org/W6850929189","https://openalex.org/W6853572851","https://openalex.org/W6870060220","https://openalex.org/W6875123106"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,8,135],"(RL)":[2],"benchmarking":[3,35],"has":[4],"long":[5],"relied":[6],"on":[7],"curves":[9],"and":[10,28,77,93,115],"cumulative":[11],"reward":[12],"tables,":[13],"yet":[14],"these":[15,40],"metrics":[16],"fail":[17],"to":[18,71,80,109,123,132,144,154],"capture":[19],"critical":[20],"design":[21],"challenges,":[22],"such":[23],"as":[24],"environment":[25,72,111],"sensitivity,":[26],"robustness,":[27],"reproducibility.":[29],"This":[30,141],"paper":[31],"introduces":[32],"a":[33,44,84,97,119],"novel":[34],"paradigm":[36],"that":[37,87,156],"rigorously":[38],"evaluates":[39],"understudied":[41],"properties":[42],"through":[43],"generative":[45],"framework":[46],"grounded":[47],"in":[48,137],"converse":[49],"optimality.":[50],"By":[51],"constructing":[52],"families":[53],"of":[54,67,91,162],"control":[55],"problems":[56],"with":[57,96],"provably":[58],"optimal":[59],"solutions,":[60],"our":[61],"method":[62],"enables":[63],"statistical":[64],"hypothesis":[65],"testing":[66],"an":[68,138],"algorithms":[69,136,158],"response":[70],"perturbations":[73],"both":[74],"during":[75],"training":[76],"post-deployment.":[78],"Central":[79],"this":[81],"approach":[82],"is":[83],"problem":[85],"generator":[86],"synthesizes":[88],"parametric":[89],"variations":[90],"dynamics":[92],"costs,":[94],"paired":[95],"sensitivity":[98,112],"evaluation":[99,146],"pipeline.":[100],"To":[101],"illustrate":[102],"the":[103,127,130],"frameworks":[104],"usefulness,":[105],"we":[106],"apply":[107],"it":[108],"compare":[110],"between":[113],"Adam":[114],"RAdam":[116],"optimizers":[117],"\u2013":[118],"case":[120],"study":[121],"designed":[122],"clarify":[124],"how":[125],"exactly":[126],"methodology":[128],"provides":[129],"means":[131],"evaluate":[133],"reinforcement":[134],"informative":[139],"way.":[140],"work":[142],"contributes":[143],"RL":[145],"by":[147],"shifting":[148],"focus":[149],"from":[150],"sample":[151],"efficiency":[152],"alone":[153],"methodologies":[155],"assess":[157],"under":[159],"conditions":[160],"reflective":[161],"practical":[163],"engineering":[164],"challenges.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}
