{"id":"https://openalex.org/W4400459471","doi":"https://doi.org/10.1007/s10846-024-02118-y","title":"Deep Model-Based Reinforcement Learning for Predictive Control of Robotic Systems with Dense and Sparse Rewards","display_name":"Deep Model-Based Reinforcement Learning for Predictive Control of Robotic Systems with Dense and Sparse Rewards","publication_year":2024,"publication_date":"2024-07-09","ids":{"openalex":"https://openalex.org/W4400459471","doi":"https://doi.org/10.1007/s10846-024-02118-y"},"language":"en","primary_location":{"id":"doi:10.1007/s10846-024-02118-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10846-024-02118-y","pdf_url":null,"source":{"id":"https://openalex.org/S91329792","display_name":"Journal of Intelligent & Robotic Systems","issn_l":"0921-0296","issn":["0921-0296","1573-0409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent & Robotic Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/s10846-024-02118-y","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100286547","display_name":"Luka Antonyshyn","orcid":null},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Luka Antonyshyn","raw_affiliation_strings":["School of Computing, Queen\u2019s University, 99 University Ave., Kingston, K7L 3N6, Ontario, Canada","School of Computing, Queen's University, 99 University Ave., Kingston, K7L 3N6, Ontario, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, Queen\u2019s University, 99 University Ave., Kingston, K7L 3N6, Ontario, Canada","institution_ids":["https://openalex.org/I204722609"]},{"raw_affiliation_string":"School of Computing, Queen's University, 99 University Ave., Kingston, K7L 3N6, Ontario, Canada","institution_ids":["https://openalex.org/I204722609"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025867957","display_name":"Sidney Givigi","orcid":"https://orcid.org/0000-0002-3829-3545"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Sidney Givigi","raw_affiliation_strings":["School of Computing, Queen\u2019s University, 99 University Ave., Kingston, K7L 3N6, Ontario, Canada","School of Computing, Queen's University, 99 University Ave., Kingston, K7L 3N6, Ontario, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, Queen\u2019s University, 99 University Ave., Kingston, K7L 3N6, Ontario, Canada","institution_ids":["https://openalex.org/I204722609"]},{"raw_affiliation_string":"School of Computing, Queen's University, 99 University Ave., Kingston, K7L 3N6, Ontario, Canada","institution_ids":["https://openalex.org/I204722609"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5025867957"],"corresponding_institution_ids":["https://openalex.org/I204722609"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":1.0353,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.73140006,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"110","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9939000010490417,"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"}},"topics":[{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9939000010490417,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9929999709129333,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9721999764442444,"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":0.8888586759567261},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7611246705055237},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7299279570579529},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.627801239490509},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6251471638679504},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.5548136830329895},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5335277915000916},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4761747717857361},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.47539839148521423},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4561362564563751},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4264358878135681},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.420462965965271},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.38393837213516235},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.13675090670585632},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10083431005477905},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.09182146191596985},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08977007865905762}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8888586759567261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7611246705055237},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7299279570579529},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.627801239490509},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6251471638679504},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.5548136830329895},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5335277915000916},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4761747717857361},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.47539839148521423},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4561362564563751},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4264358878135681},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.420462965965271},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.38393837213516235},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.13675090670585632},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10083431005477905},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.09182146191596985},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08977007865905762},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10846-024-02118-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10846-024-02118-y","pdf_url":null,"source":{"id":"https://openalex.org/S91329792","display_name":"Journal of Intelligent & Robotic Systems","issn_l":"0921-0296","issn":["0921-0296","1573-0409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent & Robotic Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10846-024-02118-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10846-024-02118-y","pdf_url":null,"source":{"id":"https://openalex.org/S91329792","display_name":"Journal of Intelligent & Robotic Systems","issn_l":"0921-0296","issn":["0921-0296","1573-0409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent & Robotic Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1471142393","display_name":null,"funder_award_id":"DG-2022-04277","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W124292005","https://openalex.org/W1981276685","https://openalex.org/W1995436378","https://openalex.org/W2002219970","https://openalex.org/W2097797606","https://openalex.org/W2560674852","https://openalex.org/W2803973384","https://openalex.org/W2877093712","https://openalex.org/W2952215314","https://openalex.org/W2962872206","https://openalex.org/W2963683522","https://openalex.org/W2973010964","https://openalex.org/W2989394062","https://openalex.org/W2992833799","https://openalex.org/W3005637364","https://openalex.org/W3008282592","https://openalex.org/W3008924647","https://openalex.org/W3009331570","https://openalex.org/W3099670724","https://openalex.org/W3153251967","https://openalex.org/W3172125541","https://openalex.org/W3211323014","https://openalex.org/W4220747123","https://openalex.org/W4285246777"],"related_works":["https://openalex.org/W1990079087","https://openalex.org/W2101188133","https://openalex.org/W4306904969","https://openalex.org/W3202234113","https://openalex.org/W4248731570","https://openalex.org/W2138720691","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698"],"abstract_inverted_index":{"Abstract":[0],"Sparse":[1],"rewards":[2],"and":[3,30,45,51,57,59,92,106,129,132,147],"sample":[4,145],"efficiency":[5,146],"are":[6,19,43,55,65],"open":[7],"areas":[8],"of":[9,14,25,119,144,153,170],"research":[10],"in":[11,38,157],"the":[12,63,117,125,137,142,151,166,171],"field":[13],"reinforcement":[15,26,79],"learning.":[16],"These":[17],"problems":[18],"especially":[20],"important":[21],"when":[22],"considering":[23],"applications":[24],"learning":[27,80,134],"to":[28,95,124],"robotics":[29],"other":[31],"cyber-physical":[32],"systems.":[33],"This":[34],"is":[35,100],"so":[36],"because":[37],"these":[39],"domains":[40],"many":[41],"tasks":[42],"goal-based":[44],"naturally":[46],"expressed":[47],"with":[48,62],"binary":[49],"successes":[50],"failures,":[52],"action":[53],"spaces":[54],"large":[56],"continuous,":[58],"real":[60,163],"interactions":[61],"environment":[64],"limited.":[66],"In":[67],"this":[68],"work,":[69],"we":[70],"propose":[71],"Deep":[72],"Value-and-Predictive-Model":[73],"Control":[74],"(DVPMC),":[75],"a":[76,103,107,120,162],"model-based":[77,133],"predictive":[78,121],"algorithm":[81,99],"for":[82],"continuous":[83],"control":[84,122],"that":[85,113],"uses":[86],"system":[87],"identification,":[88],"value":[89],"function":[90],"approximation":[91],"sampling-based":[93],"optimization":[94],"select":[96],"actions.":[97],"The":[98],"evaluated":[101],"on":[102,136,141,161],"dense":[104,126],"reward":[105,109,127,139],"sparse":[108,138],"task.":[110],"We":[111,149],"show":[112],"it":[114],"can":[115,173],"match":[116],"performance":[118,152],"approach":[123],"problem,":[128],"outperforms":[130],"model-free":[131],"algorithms":[135],"task":[140],"metrics":[143],"performance.":[148],"verify":[150],"an":[154],"agent":[155],"trained":[156],"simulation":[158],"using":[159],"DVPMC":[160],"robot":[164],"playing":[165],"reach-avoid":[167],"game.":[168],"Video":[169],"experiment":[172],"be":[174],"found":[175],"here:":[176],"https://youtu.be/0Q274kcfn4c":[177],".":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}