{"id":"https://openalex.org/W4385235996","doi":"https://doi.org/10.1109/med59994.2023.10185876","title":"Adaptive Risk Sensitive Path Integral for Model Predictive Control via Reinforcement Learning","display_name":"Adaptive Risk Sensitive Path Integral for Model Predictive Control via Reinforcement Learning","publication_year":2023,"publication_date":"2023-06-26","ids":{"openalex":"https://openalex.org/W4385235996","doi":"https://doi.org/10.1109/med59994.2023.10185876"},"language":"en","primary_location":{"id":"doi:10.1109/med59994.2023.10185876","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/med59994.2023.10185876","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st Mediterranean Conference on Control and Automation (MED)","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/A5080473137","display_name":"Hyung\u2010Jin Yoon","orcid":"https://orcid.org/0000-0003-4432-4894"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hyung-Jin Yoon","raw_affiliation_strings":["University of Illinois at Urbana-Champaign,Department of Mechanical Science and Engineering,USA","Department of Mechanical Science and Engineering, University of Illinois at Urbana-Champaign, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign,Department of Mechanical Science and Engineering,USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Department of Mechanical Science and Engineering, University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091656750","display_name":"Chuyuan Tao","orcid":null},"institutions":[{"id":"https://openalex.org/I134113660","display_name":"University of Nevada, Reno","ror":"https://ror.org/01keh0577","country_code":"US","type":"education","lineage":["https://openalex.org/I134113660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chuyuan Tao","raw_affiliation_strings":["University of Nevada,Department of Mechanical Engineering,Reno,USA","Department of Mechanical Engineering, University of Nevada, Reno, USA"],"affiliations":[{"raw_affiliation_string":"University of Nevada,Department of Mechanical Engineering,Reno,USA","institution_ids":["https://openalex.org/I134113660"]},{"raw_affiliation_string":"Department of Mechanical Engineering, University of Nevada, Reno, USA","institution_ids":["https://openalex.org/I134113660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012273541","display_name":"Hunmin Kim","orcid":"https://orcid.org/0000-0001-6689-3495"},"institutions":[{"id":"https://openalex.org/I2801518522","display_name":"Mercer University Health Sciences Center","ror":"https://ror.org/01g67by91","country_code":"US","type":"education","lineage":["https://openalex.org/I2801518522"]},{"id":"https://openalex.org/I150149174","display_name":"Mercer University","ror":"https://ror.org/04bk7v425","country_code":"US","type":"education","lineage":["https://openalex.org/I150149174"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hunmin Kim","raw_affiliation_strings":["Mercer University,Department of Electrical and Computer Engineering,USA","Department of Electrical and Computer Engineering, Mercer University, USA"],"affiliations":[{"raw_affiliation_string":"Mercer University,Department of Electrical and Computer Engineering,USA","institution_ids":["https://openalex.org/I150149174","https://openalex.org/I2801518522"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Mercer University, USA","institution_ids":["https://openalex.org/I150149174","https://openalex.org/I2801518522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029998748","display_name":"Naira Hovakimyan","orcid":"https://orcid.org/0000-0003-3850-1073"},"institutions":[{"id":"https://openalex.org/I134113660","display_name":"University of Nevada, Reno","ror":"https://ror.org/01keh0577","country_code":"US","type":"education","lineage":["https://openalex.org/I134113660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naira Hovakimyan","raw_affiliation_strings":["University of Nevada,Department of Mechanical Engineering,Reno,USA","Department of Mechanical Engineering, University of Nevada, Reno, USA"],"affiliations":[{"raw_affiliation_string":"University of Nevada,Department of Mechanical Engineering,Reno,USA","institution_ids":["https://openalex.org/I134113660"]},{"raw_affiliation_string":"Department of Mechanical Engineering, University of Nevada, Reno, USA","institution_ids":["https://openalex.org/I134113660"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089726422","display_name":"Petros G. Voulgaris","orcid":"https://orcid.org/0000-0002-2965-3246"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Petros Voulgaris","raw_affiliation_strings":["University of Illinois at Urbana-Champaign,Department of Mechanical Science and Engineering,USA","Department of Mechanical Science and Engineering, University of Illinois at Urbana-Champaign, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign,Department of Mechanical Science and Engineering,USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Department of Mechanical Science and Engineering, University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5080473137"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09645405,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"926","last_page":"931"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9966999888420105,"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":0.9966999888420105,"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":0.9932000041007996,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.984000027179718,"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/computer-science","display_name":"Computer science","score":0.7009000182151794},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.6794391870498657},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6453235745429993},{"id":"https://openalex.org/keywords/path-integral-formulation","display_name":"Path integral formulation","score":0.6291103959083557},{"id":"https://openalex.org/keywords/stochastic-differential-equation","display_name":"Stochastic differential equation","score":0.5861777067184448},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5673409104347229},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.5442606806755066},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.5367783904075623},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.48336261510849},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4780160188674927},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4724177420139313},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4665828347206116},{"id":"https://openalex.org/keywords/stochastic-control","display_name":"Stochastic control","score":0.44471290707588196},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.3864556550979614},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3097034692764282},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.27758848667144775},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18036112189292908},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16607055068016052},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12440529465675354},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.09956023097038269}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7009000182151794},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.6794391870498657},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6453235745429993},{"id":"https://openalex.org/C154018700","wikidata":"https://www.wikidata.org/wiki/Q898323","display_name":"Path integral formulation","level":3,"score":0.6291103959083557},{"id":"https://openalex.org/C51955184","wikidata":"https://www.wikidata.org/wiki/Q1545585","display_name":"Stochastic differential equation","level":2,"score":0.5861777067184448},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5673409104347229},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.5442606806755066},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.5367783904075623},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.48336261510849},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4780160188674927},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4724177420139313},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4665828347206116},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.44471290707588196},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.3864556550979614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3097034692764282},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.27758848667144775},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18036112189292908},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16607055068016052},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12440529465675354},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.09956023097038269},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/med59994.2023.10185876","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/med59994.2023.10185876","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st Mediterranean Conference on Control and Automation (MED)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W131069610","https://openalex.org/W1503185336","https://openalex.org/W1720321157","https://openalex.org/W1975711585","https://openalex.org/W2026659355","https://openalex.org/W2048469131","https://openalex.org/W2093516101","https://openalex.org/W2096035449","https://openalex.org/W2098524868","https://openalex.org/W2181845023","https://openalex.org/W2410617946","https://openalex.org/W2602963933","https://openalex.org/W2772982620","https://openalex.org/W2963355572","https://openalex.org/W2963864421","https://openalex.org/W2966348706","https://openalex.org/W3006009338","https://openalex.org/W3009536522","https://openalex.org/W3096349301","https://openalex.org/W3106296277","https://openalex.org/W3184157780","https://openalex.org/W3186532944","https://openalex.org/W4211192810","https://openalex.org/W4294692006","https://openalex.org/W6674872077","https://openalex.org/W6684921986","https://openalex.org/W6735677848","https://openalex.org/W6746717651","https://openalex.org/W6755864697","https://openalex.org/W7015099856"],"related_works":["https://openalex.org/W2943897807","https://openalex.org/W4366198066","https://openalex.org/W3120484221","https://openalex.org/W2142934230","https://openalex.org/W3047748938","https://openalex.org/W2358522863","https://openalex.org/W4386034604","https://openalex.org/W2963640567","https://openalex.org/W3112430022","https://openalex.org/W2580841121"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,23,100,109],"reinforcement":[3],"learning":[4],"framework":[5,132],"where":[6],"an":[7,10],"agent":[8],"uses":[9],"internal":[11],"nominal":[12,56],"model":[13,16,137,145],"for":[14,22],"stochastic":[15,35],"predictive":[17,146],"control":[18,33,62,94],"(MPC)":[19],"while":[20],"compensating":[21],"disturbance.":[24,45],"Our":[25],"work":[26],"builds":[27],"on":[28],"the":[29,47,51,55,59,68,71,75,78,90,116,135,139,143],"existing":[30],"risk-aware":[31,91],"optimal":[32,61],"with":[34,43,104],"differential":[36],"equations":[37],"(SDEs)":[38],"that":[39,95,133,152],"aims":[40],"to":[41,80,125],"deal":[42],"such":[44],"However,":[46],"risk":[48,140],"sensitivity":[49,141],"and":[50,138],"noise":[52,136],"strength":[53],"of":[54,77,115],"SDE":[57],"in":[58,121,149],"riskaware":[60],"are":[63],"often":[64],"heuristically":[65],"chosen.":[66],"In":[67],"proposed":[69,131],"framework,":[70],"risk-taking":[72],"policy":[73],"determines":[74],"behavior":[76],"MPC":[79,117],"be":[81,97],"risk-seeking":[82],"(exploration)":[83],"or":[84],"risk-averse":[85],"(exploitation).":[86],"Specifically,":[87],"we":[88],"employ":[89],"path":[92,147],"integral":[93,148],"can":[96],"implemented":[98],"as":[99],"Monte-Carlo":[101],"(MC)":[102],"sampling":[103,113],"fast":[105],"parallel":[106],"simulations":[107],"using":[108],"GPU.":[110],"The":[111,130],"MC":[112],"implementations":[114],"have":[118,153],"been":[119],"successful":[120],"robotic":[122],"applications":[123],"due":[124],"their":[126],"real-time":[127],"computation":[128],"capability.":[129],"adapts":[134],"outperforms":[142],"standard":[144],"simulation":[150],"environments":[151],"disturbances.":[154]},"counts_by_year":[],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}