{"id":"https://openalex.org/W4407950038","doi":"https://doi.org/10.1109/cdc56724.2024.10886483","title":"MPC4RL - A Software Package for Reinforcement Learning based on Model Predictive Control","display_name":"MPC4RL - A Software Package for Reinforcement Learning based on Model Predictive Control","publication_year":2024,"publication_date":"2024-12-16","ids":{"openalex":"https://openalex.org/W4407950038","doi":"https://doi.org/10.1109/cdc56724.2024.10886483"},"language":"en","primary_location":{"id":"doi:10.1109/cdc56724.2024.10886483","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10886483","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","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/A5081002724","display_name":"Dirk Reinhardt","orcid":"https://orcid.org/0009-0007-8775-8015"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Dirk Reinhardt","raw_affiliation_strings":["Norwegian University of Science and Technology,Department of Engineering Cybernetics,Trondheim,Norway,7034"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Norwegian University of Science and Technology,Department of Engineering Cybernetics,Trondheim,Norway,7034","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012277347","display_name":"Katrin Baumg\u00e4rtner","orcid":"https://orcid.org/0009-0004-0485-8386"},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Katrin Baumg\u00e4rtner","raw_affiliation_strings":["University Freiburg,Department of Microsystems Engineering,Freiburg,Germany,79110"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University Freiburg,Department of Microsystems Engineering,Freiburg,Germany,79110","institution_ids":["https://openalex.org/I161046081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007315476","display_name":"Jonathan Frey","orcid":"https://orcid.org/0000-0003-2771-4209"},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jonathan Frey","raw_affiliation_strings":["University Freiburg,Department of Microsystems Engineering,Freiburg,Germany,79110"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University Freiburg,Department of Microsystems Engineering,Freiburg,Germany,79110","institution_ids":["https://openalex.org/I161046081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057375078","display_name":"Moritz Diehl","orcid":"https://orcid.org/0000-0001-6556-8252"},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Moritz Diehl","raw_affiliation_strings":["University Freiburg,Department of Microsystems Engineering,Freiburg,Germany,79110"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University Freiburg,Department of Microsystems Engineering,Freiburg,Germany,79110","institution_ids":["https://openalex.org/I161046081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049645185","display_name":"S\u00e9bastien Gros","orcid":"https://orcid.org/0000-0001-6054-2133"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Sebastien Gros","raw_affiliation_strings":["Norwegian University of Science and Technology,Department of Engineering Cybernetics,Trondheim,Norway,7034"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Norwegian University of Science and Technology,Department of Engineering Cybernetics,Trondheim,Norway,7034","institution_ids":["https://openalex.org/I204778367"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5826,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.70686834,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1787","last_page":"1794"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9769999980926514,"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":0.9769999980926514,"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":0.7745903730392456},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7575497627258301},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.6161931753158569},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.47881418466567993},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3616716265678406}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7745903730392456},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7575497627258301},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.6161931753158569},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.47881418466567993},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3616716265678406}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc56724.2024.10886483","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10886483","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","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":20,"referenced_works":["https://openalex.org/W2123871098","https://openalex.org/W2537660029","https://openalex.org/W2842089854","https://openalex.org/W2901663876","https://openalex.org/W2930426397","https://openalex.org/W2948652605","https://openalex.org/W3155272911","https://openalex.org/W3207305612","https://openalex.org/W4214717370","https://openalex.org/W4225603049","https://openalex.org/W4233157081","https://openalex.org/W4285446252","https://openalex.org/W4401414310","https://openalex.org/W6684205842","https://openalex.org/W6748839928","https://openalex.org/W6752963931","https://openalex.org/W6754302822","https://openalex.org/W6766978945","https://openalex.org/W6803914020","https://openalex.org/W6804601995"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W1990079087","https://openalex.org/W3202234113","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W2101188133","https://openalex.org/W4391913857","https://openalex.org/W2556120871"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"an":[5,70],"early":[6],"software":[7,40,59],"integrating":[8],"Reinforcement":[9],"Learning":[10],"(RL)":[11],"with":[12,53],"Model":[13],"Predictive":[14],"Control":[15],"(MPC).":[16],"Our":[17,65],"aim":[18],"is":[19,68,85,107],"to":[20,30,87],"make":[21],"recent":[22],"theoretical":[23],"contributions":[24],"from":[25],"the":[26,32,44,54,94],"literature":[27],"more":[28],"accessible":[29],"both":[31],"RL":[33,45],"and":[34,91],"MPC":[35,63,77,97],"communities.":[36],"We":[37],"combine":[38],"standard":[39],"tools":[41],"developed":[42],"by":[43],"community,":[46],"such":[47],"as":[48],"Gymnasium,":[49],"stable-baselines3,":[50],"or":[51],"CleanRL":[52],"acados":[55,81],"toolbox,":[56],"a":[57,100],"widely-used":[58],"package":[60,73,84],"for":[61,79,99],"efficient":[62],"algorithms.":[64],"core":[66],"contribution":[67],"MPC4RL,":[69],"open-source":[71],"Python":[72],"that":[74],"supports":[75],"learning-enhanced":[76],"schemes":[78],"existing":[80],"implementations.":[82],"The":[83],"designed":[86],"be":[88],"modular,":[89],"extensible,":[90],"user-friendly,":[92],"facilitating":[93],"tuning":[95],"of":[96,103],"algorithms":[98],"broad":[101],"range":[102],"control":[104],"problems.":[105],"It":[106],"available":[108],"on":[109],"GitHub.":[110]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}