{"id":"https://openalex.org/W7138199872","doi":"https://doi.org/10.1609/aaai.v40i33.40024","title":"Test-driven Reinforcement Learning in Continuous Control","display_name":"Test-driven Reinforcement Learning in Continuous Control","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138199872","doi":"https://doi.org/10.1609/aaai.v40i33.40024"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i33.40024","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i33.40024","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40024/43985","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40024/43985","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114430127","display_name":"Zhao Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhao Yu","raw_affiliation_strings":["Xi'an Jiaotong University"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129644102","display_name":"Xiuping Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xiuping Wu","raw_affiliation_strings":["University of Southampton"],"affiliations":[{"raw_affiliation_string":"University of Southampton","institution_ids":["https://openalex.org/I43439940"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037785432","display_name":"Liangjun Ke","orcid":"https://orcid.org/0000-0002-2920-0853"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangjun Ke","raw_affiliation_strings":["Xi'an Jiaotong University"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5114430127"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41755889,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"33","first_page":"27996","last_page":"28004"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6862999796867371,"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":0.6862999796867371,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.08860000222921371,"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"}},{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.0697999969124794,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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":0.7742000222206116},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.559499979019165},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5428000092506409},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4941999912261963},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.44679999351501465},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4348999857902527},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4318999946117401},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.39410001039505005}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7742000222206116},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7123000025749207},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.559499979019165},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5428000092506409},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4952999949455261},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4941999912261963},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.44679999351501465},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4348999857902527},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4318999946117401},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4309000074863434},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.39410001039505005},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3522999882698059},{"id":"https://openalex.org/C94822996","wikidata":"https://www.wikidata.org/wiki/Q1777902","display_name":"Satisficing","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3222000002861023},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.32109999656677246},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C173246807","wikidata":"https://www.wikidata.org/wiki/Q7833062","display_name":"Trajectory optimization","level":3,"score":0.27090001106262207},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i33.40024","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i33.40024","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40024/43985","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i33.40024","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i33.40024","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40024/43985","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138199872.pdf","grobid_xml":"https://content.openalex.org/works/W7138199872.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0,78],"learning":[1,123,199],"(RL)":[2],"has":[3],"been":[4],"recognized":[5],"as":[6,107],"a":[7,57,76,98,134,142,168,181,247],"powerful":[8],"tool":[9],"for":[10,198,239,250],"robot":[11],"control":[12],"tasks.":[13],"RL":[14,265],"typically":[15],"employs":[16],"reward":[17,30,50,64,100,227,261],"functions":[18,88,103],"to":[19,47,91,115,149,152,173,185],"define":[20],"task":[21,59,94,135,252],"objectives":[22],"and":[23,41,110,120,193,236],"guide":[24],"agent":[25],"learning.":[26],"However,":[27],"since":[28],"the":[29,33,38,49,63,71,83,93,117,122,153,174,187,194,200,215,260],"function":[31,51,145,165],"serves":[32],"dual":[34],"purpose":[35],"of":[36,210],"defining":[37,116,128],"optimal":[39,118,154,175,195],"goal":[40],"guiding":[42,121],"learning,":[43],"it":[44],"is":[45,171],"challenging":[46],"design":[48,65,234,262],"manually,":[52],"which":[53,254],"often":[54],"results":[55,213],"in":[56,67,229,258,264],"suboptimal":[58],"representation.":[60],"To":[61],"tackle":[62],"challenge":[66],"RL,":[68],"inspired":[69],"by":[70],"satisficing":[72],"theory,":[73],"we":[74,137,179,205],"propose":[75],"Test-driven":[77],"Learning":[79],"(TdRL)":[80],"framework.":[81],"In":[82],"TdRL":[84,222,245],"framework,":[85],"multiple":[86],"test":[87],"are":[89],"used":[90],"represent":[92],"objective":[95,119],"rather":[96],"than":[97],"single":[99],"function.":[101,203],"Test":[102],"can":[104],"be":[105,256],"categorized":[106],"pass-fail":[108],"tests":[109],"indicative":[111],"tests,":[112],"each":[113],"dedicated":[114],"process,":[124],"respectively,":[125],"thereby":[126],"making":[127],"tasks":[129],"easier.":[130],"Building":[131],"upon":[132],"such":[133],"definition,":[136],"first":[138],"prove":[139],"that":[140,170,221,244],"if":[141],"trajectory":[143,155,196,201],"return":[144,164,202],"assigns":[146],"higher":[147],"returns":[148],"trajectories":[150,192],"closer":[151,172],"set,":[156],"maximum":[157],"entropy":[158],"policy":[159,169,176,230],"optimization":[160],"based":[161],"on":[162,214],"this":[163],"will":[166],"yield":[167],"set.":[177],"Then,":[178],"introduce":[180],"lexicographic":[182],"heuristic":[183],"approach":[184],"compare":[186],"relative":[188],"distance":[189],"relationship":[190],"between":[191],"set":[197],"Furthermore,":[204],"develop":[206],"an":[207],"algorithm":[208],"implementation":[209],"TdRL.":[211],"Experimental":[212],"DeepMind":[216],"Control":[217],"Suite":[218],"benchmark":[219],"demonstrate":[220],"matches":[223],"or":[224],"outperforms":[225],"handcrafted":[226],"methods":[228],"training,":[231],"with":[232],"greater":[233],"simplicity":[235],"inherent":[237],"support":[238],"multi-objective":[240],"optimization.":[241],"We":[242],"argue":[243],"offers":[246],"novel":[248],"perspective":[249],"representing":[251],"objectives,":[253],"could":[255],"helpful":[257],"addressing":[259],"challenges":[263],"applications.":[266]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}