{"id":"https://openalex.org/W7155057911","doi":"https://doi.org/10.1109/icara69401.2026.11480318","title":"Curriculum-Based Reward Function Optimization Using Deep Deterministic Policy Gradient for Rotary Inverted Pendulum: An Underactuated System","display_name":"Curriculum-Based Reward Function Optimization Using Deep Deterministic Policy Gradient for Rotary Inverted Pendulum: An Underactuated System","publication_year":2026,"publication_date":"2026-02-05","ids":{"openalex":"https://openalex.org/W7155057911","doi":"https://doi.org/10.1109/icara69401.2026.11480318"},"language":null,"primary_location":{"id":"doi:10.1109/icara69401.2026.11480318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icara69401.2026.11480318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 12th International Conference on Automation, Robotics and Applications (ICARA)","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/A5134181864","display_name":"Muhammad Talha Hassan","orcid":null},"institutions":[{"id":"https://openalex.org/I929597975","display_name":"National University of Sciences and Technology","ror":"https://ror.org/03w2j5y17","country_code":"PK","type":"education","lineage":["https://openalex.org/I929597975"]}],"countries":["PK"],"is_corresponding":true,"raw_author_name":"Muhammad Talha Hassan","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, National University of Sciences and Technology (NUST),Islamabad,Pakistan,44000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, National University of Sciences and Technology (NUST),Islamabad,Pakistan,44000","institution_ids":["https://openalex.org/I929597975"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114231461","display_name":"Suhail Ashraf","orcid":"https://orcid.org/0009-0002-8657-6651"},"institutions":[{"id":"https://openalex.org/I929597975","display_name":"National University of Sciences and Technology","ror":"https://ror.org/03w2j5y17","country_code":"PK","type":"education","lineage":["https://openalex.org/I929597975"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Shameer Ashraf","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, National University of Sciences and Technology (NUST),Islamabad,Pakistan,44000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, National University of Sciences and Technology (NUST),Islamabad,Pakistan,44000","institution_ids":["https://openalex.org/I929597975"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134206151","display_name":"Muhammad Haris","orcid":null},"institutions":[{"id":"https://openalex.org/I929597975","display_name":"National University of Sciences and Technology","ror":"https://ror.org/03w2j5y17","country_code":"PK","type":"education","lineage":["https://openalex.org/I929597975"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Muhammad Haris","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, National University of Sciences and Technology (NUST),Islamabad,Pakistan,44000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, National University of Sciences and Technology (NUST),Islamabad,Pakistan,44000","institution_ids":["https://openalex.org/I929597975"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112669333","display_name":"Muhammad Abdullah","orcid":"https://orcid.org/0000-0002-6740-6115"},"institutions":[{"id":"https://openalex.org/I929597975","display_name":"National University of Sciences and Technology","ror":"https://ror.org/03w2j5y17","country_code":"PK","type":"education","lineage":["https://openalex.org/I929597975"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Muhammad Abdullah","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, National University of Sciences and Technology (NUST),Islamabad,Pakistan,44000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, National University of Sciences and Technology (NUST),Islamabad,Pakistan,44000","institution_ids":["https://openalex.org/I929597975"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043898517","display_name":"Neelma Naz","orcid":"https://orcid.org/0000-0002-5274-8913"},"institutions":[{"id":"https://openalex.org/I929597975","display_name":"National University of Sciences and Technology","ror":"https://ror.org/03w2j5y17","country_code":"PK","type":"education","lineage":["https://openalex.org/I929597975"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Neelma Naz","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, National University of Sciences and Technology (NUST),Islamabad,Pakistan,44000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, National University of Sciences and Technology (NUST),Islamabad,Pakistan,44000","institution_ids":["https://openalex.org/I929597975"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5134181864"],"corresponding_institution_ids":["https://openalex.org/I929597975"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.92665618,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"482","last_page":"487"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.46480000019073486,"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":0.46480000019073486,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.1703999936580658,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.055399999022483826,"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/control-theory","display_name":"Control theory (sociology)","score":0.6478999853134155},{"id":"https://openalex.org/keywords/underactuation","display_name":"Underactuation","score":0.582099974155426},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4821000099182129},{"id":"https://openalex.org/keywords/gradient-method","display_name":"Gradient method","score":0.3172000050544739},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.29350000619888306},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.2888999879360199}],"concepts":[{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6478999853134155},{"id":"https://openalex.org/C88337583","wikidata":"https://www.wikidata.org/wiki/Q7883433","display_name":"Underactuation","level":3,"score":0.582099974155426},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5551999807357788},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4821000099182129},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3490000069141388},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30059999227523804},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.2678999900817871},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.266400009393692},{"id":"https://openalex.org/C55660270","wikidata":"https://www.wikidata.org/wiki/Q5164377","display_name":"Constrained optimization","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icara69401.2026.11480318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icara69401.2026.11480318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 12th International Conference on Automation, Robotics and Applications (ICARA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2807741405","https://openalex.org/W2944252781","https://openalex.org/W4388417553","https://openalex.org/W4388917943","https://openalex.org/W4394833321","https://openalex.org/W4409347437"],"related_works":[],"abstract_inverted_index":{"The":[0,99,133,145,175],"Rotary":[1],"Inverted":[2],"Pendulum":[3],"(RIP)":[4],"is":[5,15,103,125,178],"a":[6,10,87,121],"classic":[7],"example":[8],"of":[9,50,70,79,105,154],"nonlinear,":[11],"underactuated":[12,216],"system,":[13],"and":[14,58,109,151,158,192,219],"difficult":[16,41],"to":[17,45,67,171,181,184,193],"control":[18,21,37,69,84,101,138,168,196,217],"using":[19,95,127],"traditional":[20],"models.":[22],"Recent":[23],"advancements":[24],"in":[25,34,113,223],"Deep":[26,53],"Reinforcement":[27,60],"Learning":[28,61],"(DRL)":[29],"have":[30],"demonstrated":[31],"significant":[32],"promise":[33],"handling":[35],"challenging":[36],"problems":[38],"that":[39,201],"are":[40],"for":[42,63,92,214],"conventional":[43],"methods":[44],"handle.":[46],"However,":[47],"the":[48,68,77,93,96,111,114,118,136,143,149,156,159,163,167,172,182,189,202,207],"application":[49],"DRL,":[51],"especially":[52],"Deterministic":[54],"Policy":[55],"Gradient":[56],"(DDPG)":[57],"Curriculum":[59],"(CRL)":[62],"Complex":[64],"Reward":[65],"Functions":[66],"RIP":[71,94,208],"remains":[72],"underexplored.":[73],"This":[74],"study":[75],"presents":[76],"development":[78],"an":[80],"efficient":[81],"DRL":[82],"based":[83,225],"strategy":[85,204],"leveraging":[86],"dynamic":[88],"reward":[89,176],"function":[90,177],"shaping":[91],"DDPG":[97],"algorithm.":[98],"proposed":[100],"mechanism":[102],"capable":[104],"both":[106,155],"swinging":[107],"up":[108],"stabilizing":[110],"pendulum":[112,157],"upright":[115,190],"position.":[116],"For":[117],"training":[119],"process,":[120],"physics-based":[122],"simulation":[123],"environment":[124],"developed":[126],"MuJoCo":[128],"(an":[129],"advanced":[130],"physics":[131],"engine).":[132],"agent":[134],"learn":[135],"optimal":[137],"policies":[139],"through":[140],"interaction":[141],"with":[142],"environment.":[144],"state":[146],"space":[147,165],"includes":[148],"angles":[150],"angular":[152],"velocities":[153],"horizontal":[160,173],"arm,":[161],"while":[162],"action":[164],"comprises":[166],"torques":[169],"applied":[170],"arm.":[174],"designed":[179],"according":[180],"CRL":[183],"encourage":[185],"minimal":[186],"deviation":[187],"from":[188],"position":[191],"promote":[194],"smooth":[195],"actions.":[197],"Simulation":[198],"results":[199],"show":[200],"DDPG-based":[203],"reliably":[205],"stabilizes":[206],"despite":[209],"disturbances,":[210],"highlighting":[211],"DRL's":[212],"effectiveness":[213],"complex,":[215],"tasks":[218],"encouraging":[220],"further":[221],"research":[222],"learning":[224],"methods.":[226]},"counts_by_year":[],"updated_date":"2026-04-23T06:14:38.165362","created_date":"2026-04-22T00:00:00"}