{"id":"https://openalex.org/W4383108777","doi":"https://doi.org/10.1109/icra48891.2023.10161492","title":"Handling Sparse Rewards in Reinforcement Learning Using Model Predictive Control","display_name":"Handling Sparse Rewards in Reinforcement Learning Using Model Predictive Control","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383108777","doi":"https://doi.org/10.1109/icra48891.2023.10161492"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10161492","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10161492","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","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/A5069650777","display_name":"Murad Dawood","orcid":null},"institutions":[{"id":"https://openalex.org/I4387154616","display_name":"Lamarr Institute for Machine Learning and Artificial Intelligence","ror":"https://ror.org/04s11ea33","country_code":null,"type":"facility","lineage":["https://openalex.org/I135140700","https://openalex.org/I200332995","https://openalex.org/I4210098062","https://openalex.org/I4210144576","https://openalex.org/I4387154616","https://openalex.org/I4923324","https://openalex.org/I4923324"]},{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Murad Dawood","raw_affiliation_strings":["University of Bonn,Humanoid Robots Lab.,Germany","Humanoid Robots Lab., University of Bonn, Germany","Lamarr Institute for Machine Learning and Artificial Intelligence, Germany"],"affiliations":[{"raw_affiliation_string":"University of Bonn,Humanoid Robots Lab.,Germany","institution_ids":["https://openalex.org/I135140700"]},{"raw_affiliation_string":"Humanoid Robots Lab., University of Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]},{"raw_affiliation_string":"Lamarr Institute for Machine Learning and Artificial Intelligence, Germany","institution_ids":["https://openalex.org/I4387154616"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065181173","display_name":"Nils Dengler","orcid":null},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nils Dengler","raw_affiliation_strings":["University of Bonn,Humanoid Robots Lab.,Germany","Humanoid Robots Lab., University of Bonn, Germany"],"affiliations":[{"raw_affiliation_string":"University of Bonn,Humanoid Robots Lab.,Germany","institution_ids":["https://openalex.org/I135140700"]},{"raw_affiliation_string":"Humanoid Robots Lab., University of Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069729988","display_name":"Jorge de Heuvel","orcid":"https://orcid.org/0000-0002-4493-6148"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jorge de Heuvel","raw_affiliation_strings":["University of Bonn,Humanoid Robots Lab.,Germany","Humanoid Robots Lab., University of Bonn, Germany"],"affiliations":[{"raw_affiliation_string":"University of Bonn,Humanoid Robots Lab.,Germany","institution_ids":["https://openalex.org/I135140700"]},{"raw_affiliation_string":"Humanoid Robots Lab., University of Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103231515","display_name":"Maren Bennewitz","orcid":"https://orcid.org/0000-0003-4343-3028"},"institutions":[{"id":"https://openalex.org/I4387154616","display_name":"Lamarr Institute for Machine Learning and Artificial Intelligence","ror":"https://ror.org/04s11ea33","country_code":null,"type":"facility","lineage":["https://openalex.org/I135140700","https://openalex.org/I200332995","https://openalex.org/I4210098062","https://openalex.org/I4210144576","https://openalex.org/I4387154616","https://openalex.org/I4923324","https://openalex.org/I4923324"]},{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Maren Bennewitz","raw_affiliation_strings":["University of Bonn,Humanoid Robots Lab.,Germany","Lamarr Institute for Machine Learning and Artificial Intelligence, Germany","Humanoid Robots Lab., University of Bonn, Germany"],"affiliations":[{"raw_affiliation_string":"University of Bonn,Humanoid Robots Lab.,Germany","institution_ids":["https://openalex.org/I135140700"]},{"raw_affiliation_string":"Lamarr Institute for Machine Learning and Artificial Intelligence, Germany","institution_ids":["https://openalex.org/I4387154616"]},{"raw_affiliation_string":"Humanoid Robots Lab., University of Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5069650777"],"corresponding_institution_ids":["https://openalex.org/I135140700","https://openalex.org/I4387154616"],"apc_list":null,"apc_paid":null,"fwci":2.2615,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.90289941,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"879","last_page":"885"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9866999983787537,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.9056000113487244,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8712038993835449},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7878049612045288},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6078400611877441},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5968453288078308},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5231426954269409},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.5220280289649963},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4964624047279358},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4776543378829956},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46307432651519775},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4572027623653412},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.451445996761322},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0805065929889679}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8712038993835449},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7878049612045288},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6078400611877441},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5968453288078308},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5231426954269409},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.5220280289649963},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4964624047279358},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4776543378829956},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46307432651519775},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4572027623653412},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.451445996761322},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0805065929889679},{"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},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10161492","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10161492","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","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":45,"referenced_works":["https://openalex.org/W1923344279","https://openalex.org/W1974164103","https://openalex.org/W2158782408","https://openalex.org/W2167340365","https://openalex.org/W2607198029","https://openalex.org/W2741122588","https://openalex.org/W2788862220","https://openalex.org/W2794683864","https://openalex.org/W2795561664","https://openalex.org/W2884151543","https://openalex.org/W2885665445","https://openalex.org/W2901291754","https://openalex.org/W2904246096","https://openalex.org/W2963099939","https://openalex.org/W2963129648","https://openalex.org/W3006499227","https://openalex.org/W3013225982","https://openalex.org/W3037625705","https://openalex.org/W3091686107","https://openalex.org/W3119193920","https://openalex.org/W3129896193","https://openalex.org/W3130288902","https://openalex.org/W3142049818","https://openalex.org/W3153704809","https://openalex.org/W3155794842","https://openalex.org/W3155818342","https://openalex.org/W3189001389","https://openalex.org/W3200809500","https://openalex.org/W3207305612","https://openalex.org/W4206874491","https://openalex.org/W4221160486","https://openalex.org/W4289115845","https://openalex.org/W4298112294","https://openalex.org/W4300799055","https://openalex.org/W6675999342","https://openalex.org/W6736609842","https://openalex.org/W6740801417","https://openalex.org/W6742461812","https://openalex.org/W6748839928","https://openalex.org/W6749499340","https://openalex.org/W6756486208","https://openalex.org/W6756848961","https://openalex.org/W6768977950","https://openalex.org/W6799003931","https://openalex.org/W6810137820"],"related_works":["https://openalex.org/W1990079087","https://openalex.org/W3202234113","https://openalex.org/W4306904969","https://openalex.org/W2101188133","https://openalex.org/W4248731570","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2381210024"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,185],"(RL)":[2],"has":[3],"recently":[4],"proven":[5],"great":[6,154],"success":[7,163],"in":[8,56,72,118,133,141,160,191],"various":[9],"domains.":[10,100],"Yet,":[11],"the":[12,15,33,45,60,68,123,134,183,192],"design":[13],"of":[14,59,99,136,162,169,194],"reward":[16,39,47,70,83,120,126],"function":[17],"requires":[18],"detailed":[19],"domain":[20],"expertise":[21],"and":[22,143,171],"tedious":[23],"fine-tuning":[24],"to":[25,31,77,82,95,104],"ensure":[26],"that":[27,90,176],"agents":[28,117],"are":[29],"able":[30],"learn":[32],"desired":[34],"behaviour.":[35],"Using":[36],"a":[37,49,96,147,188],"sparse":[38,46,69,119,195],"conveniently":[40],"mitigates":[41],"these":[42],"challenges.":[43],"However,":[44],"represents":[48],"challenge":[50],"on":[51],"its":[52],"own,":[53],"often":[54],"resulting":[55],"unsuccessful":[57],"training":[58,115],"agent.":[61],"In":[62],"this":[63],"paper,":[64],"we":[65,102,128],"therefore":[66],"address":[67],"problem":[71],"RL.":[73],"Our":[74,173],"goal":[75],"is":[76],"find":[78],"an":[79,111,179],"effective":[80],"alternative":[81],"shaping,":[84,127],"without":[85],"using":[86],"costly":[87],"human":[88],"demonstrations,":[89],"would":[91],"also":[92],"be":[93],"applicable":[94],"wide":[97],"range":[98],"Hence,":[101],"propose":[103],"use":[105],"model":[106],"predictive":[107],"control":[108],"(MPC)":[109],"as":[110,165,167,178],"experience":[112,180],"source":[113,181],"for":[114,125,187],"RL":[116,158],"environments.":[121],"Without":[122],"need":[124],"successfully":[129],"apply":[130],"our":[131],"approach":[132],"field":[135],"mobile":[137],"robot":[138],"navigation":[139],"both":[140],"simulation":[142],"real-world":[144],"experiments":[145,174],"with":[146],"Kuboki":[148],"Turtlebot":[149],"2.":[150],"We":[151],"furthermore":[152],"demonstrate":[153],"improvement":[155],"over":[156],"pure":[157],"algorithms":[159],"terms":[161],"rate":[164],"well":[166],"number":[168],"collisions":[170],"timeouts.":[172],"show":[175],"MPC":[177],"improves":[182],"agent's":[184],"process":[186],"given":[189],"task":[190],"case":[193],"rewards.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-29T08:15:47.926485","created_date":"2025-10-10T00:00:00"}