{"id":"https://openalex.org/W4385484633","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191867","title":"Reducing the Cost of Cycle-Time Tuning for Real-World Policy Optimization","display_name":"Reducing the Cost of Cycle-Time Tuning for Real-World Policy Optimization","publication_year":2023,"publication_date":"2023-06-18","ids":{"openalex":"https://openalex.org/W4385484633","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191867"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn54540.2023.10191867","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn54540.2023.10191867","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","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/A5052295104","display_name":"Homayoon Farrahi","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Homayoon Farrahi","raw_affiliation_strings":["University of Alberta,Department of Computing Science,Edmonton,Canada","Department of Computing Science, University of Alberta, Edmonton, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta,Department of Computing Science,Edmonton,Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102815213","display_name":"A. Rupam Mahmood","orcid":"https://orcid.org/0000-0002-2640-1844"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"A. Rupam Mahmood","raw_affiliation_strings":["University of Alberta,Department of Computing Science,Edmonton,Canada","Department of Computing Science, University of Alberta, Edmonton, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta,Department of Computing Science,Edmonton,Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08531851,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9782999753952026,"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":0.9598000049591064,"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/benchmark","display_name":"Benchmark (surveying)","score":0.8116047382354736},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.783048152923584},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6917650103569031},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.611325740814209},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.6089000105857849},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5690141916275024},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5262150764465332},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39868783950805664},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.19699841737747192},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17999303340911865}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8116047382354736},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.783048152923584},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6917650103569031},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.611325740814209},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.6089000105857849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5690141916275024},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5262150764465332},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39868783950805664},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.19699841737747192},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17999303340911865},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn54540.2023.10191867","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn54540.2023.10191867","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320314212","display_name":"Alberta Machine Intelligence Institute","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1520048352","https://openalex.org/W1522301498","https://openalex.org/W2113501460","https://openalex.org/W2143803054","https://openalex.org/W2736601468","https://openalex.org/W2787938642","https://openalex.org/W2788842776","https://openalex.org/W2897445793","https://openalex.org/W2904246096","https://openalex.org/W2907537824","https://openalex.org/W2913577890","https://openalex.org/W2950268955","https://openalex.org/W2963184939","https://openalex.org/W2981030070","https://openalex.org/W2987973365","https://openalex.org/W2997895572","https://openalex.org/W3024597329","https://openalex.org/W3036619998","https://openalex.org/W3104173699","https://openalex.org/W3121342653","https://openalex.org/W3128350768","https://openalex.org/W3154264273","https://openalex.org/W3206200647","https://openalex.org/W3215497921","https://openalex.org/W4287979179","https://openalex.org/W6631190155","https://openalex.org/W6681183203","https://openalex.org/W6741002519","https://openalex.org/W6748839928","https://openalex.org/W6754615820","https://openalex.org/W6755575430","https://openalex.org/W6757380569","https://openalex.org/W6757592117","https://openalex.org/W6758907457","https://openalex.org/W6767084887","https://openalex.org/W6777295057","https://openalex.org/W6780559895","https://openalex.org/W6910476156"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W4321353415","https://openalex.org/W2913146933","https://openalex.org/W2745001401","https://openalex.org/W2372385138","https://openalex.org/W4296359239"],"abstract_inverted_index":{"Continuous-time":[0],"reinforcement":[1],"learning":[2,35,181],"tasks":[3],"commonly":[4],"use":[5],"discrete":[6],"steps":[7],"of":[8,33,44,64,82,172],"fixed":[9],"cycle":[10,46,72,95,129,142,174,185,220,230],"times":[11],"for":[12,22,41,51,127,135,169,183,194,218,234,249],"actions.":[13],"As":[14],"practitioners":[15],"need":[16,37],"to":[17,38,87,109,214],"choose":[18],"the":[19,31,34,45,59,79,99,141,153,162,173,229],"action-cycle":[20],"time":[21,96,231],"a":[23,26,75,94,191,205,235,240],"given":[24,236],"task,":[25,207],"significant":[27,192],"concern":[28],"is":[29,49,102,211,232,239],"whether":[30],"hyper-parameters":[32,81,107,119,138],"algorithm":[36],"be":[39],"re-tuned":[40],"each":[42,128,219],"choice":[43],"time,":[47,175],"which":[48],"prohibitive":[50],"real-world":[52,150,195,250],"robotics.":[53],"In":[54,144],"this":[55],"work,":[56],"we":[57,90],"investigate":[58],"widely-used":[60],"baseline":[61,80,106,118,163],"hyper-parameter":[62,247],"values":[63,126],"two":[65],"policy":[66,251],"gradient":[67],"algorithms\u2014PPO":[68],"and":[69,114,149,176,238,245],"SAC\u2014across":[70],"different":[71,97],"times.":[73],"Using":[74],"benchmark":[76],"task":[77,100,237],"where":[78],"both":[83,112],"algorithms":[84],"were":[85],"shown":[86],"work":[88],"well,":[89],"reveal":[91],"that":[92],"when":[93],"than":[98,123],"default":[101],"chosen,":[103],"PPO":[104,113],"with":[105,116,165],"fails":[108],"learn.":[110],"Moreover,":[111],"SAC":[115],"their":[117,124],"perform":[120],"substantially":[121],"worse":[122],"tuned":[125],"time.":[130,143,186,221],"We":[131],"propose":[132],"novel":[133],"approaches":[134,155,199],"setting":[136],"these":[137],"based":[139],"on":[140,147,204],"our":[145,198],"experiments":[146],"simulated":[148],"robotic":[151],"tasks,":[152],"proposed":[154],"performed":[156],"at":[157],"least":[158],"as":[159,161,197],"well":[160],"hyper-parameters,":[164],"significantly":[166],"better":[167],"performance":[168],"most":[170],"choices":[171],"did":[177],"not":[178],"result":[179],"in":[180],"failure":[182],"any":[184],"Hyper-parameter":[187],"tuning":[188,203,217,227,248],"still":[189],"remains":[190],"barrier":[193],"robotics,":[196],"require":[200],"some":[201],"initial":[202],"new":[206],"even":[208],"though":[209],"it":[210],"negligible":[212],"compared":[213],"an":[215],"extensive":[216,244],"Our":[222],"approach":[223],"requires":[224],"no":[225],"additional":[226],"after":[228],"changed":[233],"step":[241],"toward":[242],"avoiding":[243],"costly":[246],"optimization.":[252]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}