{"id":"https://openalex.org/W4400799081","doi":"https://doi.org/10.1145/3626203.3670581","title":"Tuning Apex DQN: A Reinforcement Learning based Deep Q-Network Algorithm","display_name":"Tuning Apex DQN: A Reinforcement Learning based Deep Q-Network Algorithm","publication_year":2024,"publication_date":"2024-07-17","ids":{"openalex":"https://openalex.org/W4400799081","doi":"https://doi.org/10.1145/3626203.3670581"},"language":"en","primary_location":{"id":"doi:10.1145/3626203.3670581","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626203.3670581","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626203.3670581?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Practice and Experience in Advanced Research Computing 2024: Human Powered Computing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3626203.3670581?download=true","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090358228","display_name":"Dhani Ruhela","orcid":"https://orcid.org/0009-0007-9618-5976"},"institutions":[{"id":"https://openalex.org/I2802886717","display_name":"Westwood College","ror":"https://ror.org/05kjfpp30","country_code":"US","type":"education","lineage":["https://openalex.org/I2802886717"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhani Ruhela","raw_affiliation_strings":["None, Westwood High School, USA"],"raw_orcid":"https://orcid.org/0009-0007-9618-5976","affiliations":[{"raw_affiliation_string":"None, Westwood High School, USA","institution_ids":["https://openalex.org/I2802886717"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012040774","display_name":"Amit Ruhela","orcid":"https://orcid.org/0000-0001-6547-714X"},"institutions":[{"id":"https://openalex.org/I4388891828","display_name":"Texas Advanced Computing Center","ror":"https://ror.org/00xg4bh43","country_code":null,"type":"facility","lineage":["https://openalex.org/I4388891828","https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amit Ruhela","raw_affiliation_strings":["HPC Tools, Texas Advanced Computing Center, USA"],"raw_orcid":"https://orcid.org/0000-0001-6547-714X","affiliations":[{"raw_affiliation_string":"HPC Tools, Texas Advanced Computing Center, USA","institution_ids":["https://openalex.org/I4388891828"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09081213,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.07779999822378159,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.07779999822378159,"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/T10320","display_name":"Neural Networks and Applications","score":0.06639999896287918,"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/T14011","display_name":"Elevator Systems and Control","score":0.062300000339746475,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7802765369415283},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7041265368461609},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5263206362724304},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5060316920280457},{"id":"https://openalex.org/keywords/apex","display_name":"Apex (geometry)","score":0.48770031332969666},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4442565441131592},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15424731373786926}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7802765369415283},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7041265368461609},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5263206362724304},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5060316920280457},{"id":"https://openalex.org/C67139541","wikidata":"https://www.wikidata.org/wiki/Q2858200","display_name":"Apex (geometry)","level":2,"score":0.48770031332969666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4442565441131592},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15424731373786926},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3626203.3670581","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626203.3670581","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626203.3670581?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Practice and Experience in Advanced Research Computing 2024: Human Powered Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3626203.3670581","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626203.3670581","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626203.3670581?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Practice and Experience in Advanced Research Computing 2024: Human Powered Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400799081.pdf","grobid_xml":"https://content.openalex.org/works/W4400799081.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W3043992826","https://openalex.org/W4236520343"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W2361647908","https://openalex.org/W2937181779","https://openalex.org/W2537866915","https://openalex.org/W2089415692","https://openalex.org/W4294873804"],"abstract_inverted_index":{"Technological":[0],"inventions":[1],"in":[2,238],"the":[3,32,55,58,107,115,129,170,173,177,187,190,212,219,225,230,233],"last":[4],"decade":[5],"have":[6,28],"increasingly":[7],"geared":[8],"towards":[9],"developing":[10],"autonomous":[11],"systems":[12],"that":[13,125,202,223,250],"belong":[14],"to":[15,81,105,127,168,228],"robotics,":[16],"healthcare,":[17],"games,":[18],"smart":[19],"grids,":[20],"finance":[21],"and":[22,45,48,137,156],"other":[23],"domains.":[24],"Such":[25],"advanced":[26],"developments":[27],"become":[29],"possible":[30,209],"through":[31],"incredible":[33],"capabilities":[34],"of":[35,172,180,192,199,208,214,232,235],"Deep":[36,117],"Reinforcement":[37],"Learning":[38],"(DRL),":[39],"which":[40],"combines":[41],"reinforcement":[42],"learning":[43,47,53,86],"(RL)":[44],"deep":[46],"resembles":[49],"how":[50],"humans":[51],"begin":[52],"from":[54,57],"world":[56],"very":[59],"moment":[60],"they":[61],"are":[62],"born.":[63],"In":[64],"RL,":[65],"a":[66,97,121,196,206,246],"machine":[67],"or":[68,77,91,99,183],"an":[69,73,83,93,144],"agent":[70,94,103],"interacts":[71],"with":[72,88,114,205,245],"environment":[74],"by":[75,110,186,256],"exploring":[76],"exploiting":[78],"various":[79,160],"policies":[80],"reach":[82],"outcome.":[84],"The":[85,102],"happens":[87],"each":[89],"reward":[90,109],"punishment":[92],"receives,":[95],"attaining":[96],"desirable":[98],"undesirable":[100],"state.":[101],"aims":[104,126],"maximize":[106,128],"cumulative":[108],"interacting":[111],"numerous":[112],"times":[113],"environment.":[116],"Q-Networks":[118],"(DQN)":[119],"is":[120,165,218],"powerful":[122],"RL":[123,151,174],"technique":[124],"action-value":[130],"function":[131],"(also":[132],"known":[133],"as":[134],"Q":[135],"values)":[136],"achieve":[138],"exceptional":[139],"performance.":[140],"Ray\u2019s":[141],"RLLib":[142],"library,":[143,146],"open-source":[145],"supports":[147],"production-level,":[148],"highly":[149],"distributed":[150],"algorithms":[152,237],"while":[153],"maintaining":[154],"unified":[155],"straightforward":[157],"APIs":[158],"for":[159],"industry":[161],"applications.":[162],"However,":[163],"it":[164],"incredibly":[166],"challenging":[167],"optimize":[169],"performance":[171,231,254],"algorithms,":[175],"given":[176],"vast":[178],"number":[179],"tuning":[181,259],"knobs":[182,194],"parameters":[184,227],"supported":[185],"library.":[188],"Understanding":[189],"behavior":[191],"these":[193],"demands":[195],"significant":[197],"amount":[198],"computing":[200],"resources":[201],"execute":[203],"applications":[204],"range":[207],"values.":[210],"To":[211],"best":[213],"our":[215],"belief,":[216],"this":[217],"first":[220],"research":[221],"work":[222],"exposes":[224],"critical":[226],"tune":[229],"class":[234],"DQN":[236],"RLLib.":[239],"A":[240],"thorough":[241],"investigation":[242],"was":[243],"performed":[244],"famous":[247],"Cartpole":[248],"game":[249],"indicated":[251],"over":[252],"2x":[253],"improvements":[255],"selecting":[257],"appropriate":[258],"knobs.":[260]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}