{"id":"https://openalex.org/W4296474719","doi":"https://doi.org/10.1109/cog51982.2022.9893715","title":"Towards verifiable Benchmarks for Reinforcement Learning","display_name":"Towards verifiable Benchmarks for Reinforcement Learning","publication_year":2022,"publication_date":"2022-08-21","ids":{"openalex":"https://openalex.org/W4296474719","doi":"https://doi.org/10.1109/cog51982.2022.9893715"},"language":"en","primary_location":{"id":"doi:10.1109/cog51982.2022.9893715","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog51982.2022.9893715","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"},"type":"article","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/A5019298830","display_name":"Matthias M\u00fcller-Brockhausen","orcid":"https://orcid.org/0000-0002-2107-2180"},"institutions":[{"id":"https://openalex.org/I210716285","display_name":"University of Applied Sciences Leiden","ror":"https://ror.org/0093src13","country_code":"NL","type":"education","lineage":["https://openalex.org/I210716285"]},{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Matthias Muller-Brockhausen","raw_affiliation_strings":["Leiden Institute of Advanced Computer Science (LIACS), Leiden University,The Netherlands","Leiden Institute of Advanced Computer Science (LIACS), Leiden University, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Leiden Institute of Advanced Computer Science (LIACS), Leiden University,The Netherlands","institution_ids":["https://openalex.org/I121797337","https://openalex.org/I210716285"]},{"raw_affiliation_string":"Leiden Institute of Advanced Computer Science (LIACS), Leiden University, The Netherlands","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085542421","display_name":"Aske Plaat","orcid":"https://orcid.org/0000-0001-7202-3322"},"institutions":[{"id":"https://openalex.org/I210716285","display_name":"University of Applied Sciences Leiden","ror":"https://ror.org/0093src13","country_code":"NL","type":"education","lineage":["https://openalex.org/I210716285"]},{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Aske Plaat","raw_affiliation_strings":["Leiden Institute of Advanced Computer Science (LIACS), Leiden University,The Netherlands","Leiden Institute of Advanced Computer Science (LIACS), Leiden University, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Leiden Institute of Advanced Computer Science (LIACS), Leiden University,The Netherlands","institution_ids":["https://openalex.org/I121797337","https://openalex.org/I210716285"]},{"raw_affiliation_string":"Leiden Institute of Advanced Computer Science (LIACS), Leiden University, The Netherlands","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062774048","display_name":"Mike Preu\u00df","orcid":"https://orcid.org/0000-0003-4681-1346"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]},{"id":"https://openalex.org/I210716285","display_name":"University of Applied Sciences Leiden","ror":"https://ror.org/0093src13","country_code":"NL","type":"education","lineage":["https://openalex.org/I210716285"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Mike Preuss","raw_affiliation_strings":["Leiden Institute of Advanced Computer Science (LIACS), Leiden University,The Netherlands","Leiden Institute of Advanced Computer Science (LIACS), Leiden University, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Leiden Institute of Advanced Computer Science (LIACS), Leiden University,The Netherlands","institution_ids":["https://openalex.org/I121797337","https://openalex.org/I210716285"]},{"raw_affiliation_string":"Leiden Institute of Advanced Computer Science (LIACS), Leiden University, The Netherlands","institution_ids":["https://openalex.org/I121797337"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019298830"],"corresponding_institution_ids":["https://openalex.org/I121797337","https://openalex.org/I210716285"],"apc_list":null,"apc_paid":null,"fwci":0.2651,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6136678,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"10","issue":null,"first_page":"159","last_page":"166"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9991999864578247,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9991999864578247,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9771999716758728,"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/computer-science","display_name":"Computer science","score":0.8853497505187988},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.82975172996521},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.8009617328643799},{"id":"https://openalex.org/keywords/verifiable-secret-sharing","display_name":"Verifiable secret sharing","score":0.6963115334510803},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6854004859924316},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5417140126228333},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.5043047666549683},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5037979483604431},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4948984980583191},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.49094608426094055},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.47924187779426575},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4662173390388489},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.22140610218048096}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8853497505187988},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.82975172996521},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8009617328643799},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.6963115334510803},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6854004859924316},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5417140126228333},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.5043047666549683},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5037979483604431},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4948984980583191},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.49094608426094055},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.47924187779426575},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4662173390388489},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.22140610218048096},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cog51982.2022.9893715","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog51982.2022.9893715","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarlypublications.universiteitleiden.nl:item_4251820","is_oa":false,"landing_page_url":"https://hdl.handle.net/1887/4251820","pdf_url":null,"source":{"id":"https://openalex.org/S4306400850","display_name":"Leiden Repository (Leiden University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I121797337","host_organization_name":"Leiden University","host_organization_lineage":["https://openalex.org/I121797337"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2022 IEEE Conference on Games (CoG)","raw_type":"Text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1574680346","https://openalex.org/W1743861851","https://openalex.org/W2076337359","https://openalex.org/W2126316555","https://openalex.org/W2516678343","https://openalex.org/W2569788251","https://openalex.org/W2581790101","https://openalex.org/W2590549092","https://openalex.org/W2736601468","https://openalex.org/W2747402019","https://openalex.org/W2754517384","https://openalex.org/W2765493561","https://openalex.org/W2767922802","https://openalex.org/W2919614896","https://openalex.org/W2922504922","https://openalex.org/W2941355526","https://openalex.org/W2963809228","https://openalex.org/W2964053787","https://openalex.org/W2974927186","https://openalex.org/W2976771233","https://openalex.org/W2982316857","https://openalex.org/W2994073215","https://openalex.org/W2996037775","https://openalex.org/W3009584650","https://openalex.org/W3011706575","https://openalex.org/W3013688454","https://openalex.org/W3020386461","https://openalex.org/W3037952601","https://openalex.org/W3047290399","https://openalex.org/W3104734738","https://openalex.org/W3127881383","https://openalex.org/W3133768154","https://openalex.org/W3137572436","https://openalex.org/W3168730776","https://openalex.org/W3188832256","https://openalex.org/W3207115452","https://openalex.org/W3214897310","https://openalex.org/W3216772467","https://openalex.org/W4254098104","https://openalex.org/W4285740195","https://openalex.org/W4287204036","https://openalex.org/W4288631797","https://openalex.org/W4298324247","https://openalex.org/W6741002519","https://openalex.org/W6758447138","https://openalex.org/W6761839350","https://openalex.org/W6771750343","https://openalex.org/W6772005887","https://openalex.org/W6774583691","https://openalex.org/W6775341171","https://openalex.org/W6780413722","https://openalex.org/W6780559895","https://openalex.org/W6796426860","https://openalex.org/W6804601995"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2000169967","https://openalex.org/W2112883198"],"abstract_inverted_index":{"Reinforcement":[0,49],"Learning":[1,50],"(RL)":[2],"is":[3,34,84,196],"one":[4],"of":[5,23,117,123,152,158,163,214,247],"the":[6,37,101,115,188],"most":[7,43],"dynamic":[8],"research":[9],"areas":[10],"in":[11,48,126,131,170,187,235],"Game":[12],"AI":[13,15,45],"and":[14,19,138,161,191,202],"as":[16,27,71,82,206],"a":[17,20,210,230,245],"whole,":[18],"wide":[21],"variety":[22,246],"games":[24],"are":[25,58,64],"used":[26,65,234],"its":[28],"prominent":[29],"test":[30],"problems.":[31],"However,":[32],"it":[33,83],"subject":[35],"to":[36,66,86,100,105,135,200,216,222,229],"replicability":[38],"crisis":[39],"that":[40,77,110,177,182],"currently":[41],"affects":[42],"algorithmic":[44],"research.":[46],"Benchmarking":[47],"could":[51],"be":[52],"improved":[53],"through":[54],"verifiable":[55],"results.":[56,108],"There":[57],"numerous":[59],"benchmark":[60],"environments":[61,129],"whose":[62],"scores":[63],"compare":[67],"different":[68],"algorithms,":[69],"such":[70],"Atari.":[72],"Nevertheless,":[73],"reviewers":[74,134],"must":[75],"trust":[76],"figures":[78],"represent":[79],"truthful":[80],"values,":[81],"difficult":[85],"reproduce":[87],"an":[88,156],"exact":[89],"training":[90],"curve.":[91],"We":[92,173],"propose":[93],"improving":[94],"this":[95],"situation":[96],"by":[97],"providing":[98],"access":[99],"original":[102],"evaluation":[103,141],"data":[104,165,211],"validate":[106],"study":[107],"To":[109],"end,":[111],"we":[112],"rely":[113],"on":[114],"concept":[116],"replay":[118,207],"traces.":[119],"These":[120],"allow":[121,209],"re-simulation":[122],"action":[124],"sequences":[125],"deterministic":[127],"RL":[128,190,237],"and,":[130],"turn,":[132],"enable":[133],"verify,":[136],"re-use,":[137],"manually":[139],"inspect":[140],"results":[142,243],"without":[143],"needing":[144],"large":[145],"compute":[146],"clusters.":[147],"It":[148],"also":[149],"permits":[150],"validation":[151],"presented":[153],"reward":[154],"graphs,":[155],"inspection":[157],"individual":[159],"episodes,":[160],"re-use":[162],"result":[164],"(baselines)":[166],"for":[167,225,244],"proper":[168],"comparison":[169],"follow-up":[171],"papers.":[172],"offer":[174],"plug-and-play":[175],"code":[176],"works":[178],"with":[179],"Gym":[180],"so":[181],"our":[183],"measures":[184],"fit":[185],"well":[186],"existing":[189],"reproducibility":[192],"eco-system.":[193],"Our":[194],"approach":[195],"freely":[197],"available,":[198],"easy":[199],"use,":[201],"adds":[203],"minimal":[204],"overhead,":[205],"traces":[208],"compression":[212],"ratio":[213],"up":[215],"$\\approx":[217],"10^{4}$:":[218],"1":[219],"(94":[220],"GB":[221],"8":[223],"MB":[224],"Atari":[226],"Pong)":[227],"compared":[228],"regular":[231],"MDP":[232],"trace":[233],"offline":[236],"datasets.":[238],"The":[239],"paper":[240],"presents":[241],"proof-of-concept":[242],"games.":[248]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}