{"id":"https://openalex.org/W4366208233","doi":"https://doi.org/10.48550/arxiv.2304.07219","title":"Model Predictive Control with Self-supervised Representation Learning","display_name":"Model Predictive Control with Self-supervised Representation Learning","publication_year":2023,"publication_date":"2023-04-14","ids":{"openalex":"https://openalex.org/W4366208233","doi":"https://doi.org/10.48550/arxiv.2304.07219"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2304.07219","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.07219","pdf_url":"https://arxiv.org/pdf/2304.07219","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2304.07219","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Matthies, Jonas","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthies, Jonas","raw_affiliation_strings":["Knowledge Technology , Department of Informatics , University of Hamburg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Knowledge Technology , Department of Informatics , University of Hamburg","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042086036","display_name":"Muhammad Burhan Hafez","orcid":"https://orcid.org/0000-0003-1670-8962","observed_orcids":["https://orcid.org/0000-0003-1670-8962"]},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hafez, Muhammad Burhan","raw_affiliation_strings":["Knowledge Technology , Department of Informatics , University of Hamburg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Knowledge Technology , Department of Informatics , University of Hamburg","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kotb, Mostafa","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kotb, Mostafa","raw_affiliation_strings":["Knowledge Technology , Department of Informatics , University of Hamburg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Knowledge Technology , Department of Informatics , University of Hamburg","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033486668","display_name":"Stefan Wermter","orcid":"https://orcid.org/0000-0003-1343-4775","observed_orcids":["https://orcid.org/0000-0003-1343-4775"]},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wermter, Stefan","raw_affiliation_strings":["Knowledge Technology , Department of Informatics , University of Hamburg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Knowledge Technology , Department of Informatics , University of Hamburg","institution_ids":["https://openalex.org/I159176309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I159176309"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980000257492065,"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":0.9980000257492065,"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":0.0013000000035390258,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":9.999999747378752e-05,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"model predictive control","score":0.9950000047683716},{"id":"https://openalex.org/keywords/self-supervised-representation-learning","display_name":"self-supervised representation learning","score":0.9679999947547913},{"id":"https://openalex.org/keywords/world-models","display_name":"world models","score":0.7829999923706055},{"id":"https://openalex.org/keywords/latent-state-representation","display_name":"latent state representation","score":0.7549999952316284},{"id":"https://openalex.org/keywords/sample-efficiency","display_name":"sample efficiency","score":0.699999988079071},{"id":"https://openalex.org/keywords/value-function-estimation","display_name":"value function estimation","score":0.5680000185966492},{"id":"https://openalex.org/keywords/q-function","display_name":"Q-function","score":0.4099999964237213}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7220110893249512},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.7013993859291077},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.6709408164024353},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5827535390853882},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5603666305541992},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5473863482475281},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.541724681854248},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.5282280445098877},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5146773457527161},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5052652955055237},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4281372129917145},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.425215482711792},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4104557931423187},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30765676498413086},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2418445348739624},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1639167070388794},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08205878734588623},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2304.07219","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.07219","pdf_url":"https://arxiv.org/pdf/2304.07219","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:eprints.soton.ac.uk:496838","doi":null,"is_oa":true,"landing_page_url":"https://eprints.soton.ac.uk/id/eprint/496838/1/preprint.pdf","pdf_url":"https://eprints.soton.ac.uk/496838/1/preprint.pdf","source":{"id":"https://openalex.org/S4306401019","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"NonPeerReviewed"},{"id":"doi:10.48550/arxiv.2304.07219","doi":"https://doi.org/10.48550/arxiv.2304.07219","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2304.07219","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2304.07219","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.07219","pdf_url":"https://arxiv.org/pdf/2304.07219","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4366208233.pdf","grobid_xml":"https://content.openalex.org/works/W4366208233.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4221164079","https://openalex.org/W4360604818","https://openalex.org/W3127391635","https://openalex.org/W4403322756","https://openalex.org/W3110922453","https://openalex.org/W7161690845","https://openalex.org/W3175558129","https://openalex.org/W4391021839","https://openalex.org/W7220726941","https://openalex.org/W6929523472"],"abstract_inverted_index":{"Over":[0],"the":[1,25,30,37,45,63,65,87,108,112,145,152,159,164,168,172,212],"last":[2],"few":[3],"years,":[4],"we":[5,150],"have":[6,49,181],"not":[7],"seen":[8],"any":[9],"major":[10],"developments":[11],"in":[12,93],"model-free":[13],"or":[14,41,57],"model-based":[15],"learning":[16,185],"methods":[17],"that":[18,163],"would":[19],"make":[20],"one":[21,88],"obsolete":[22],"relative":[23],"to":[24,101,120,127,143,180,202],"other.":[26],"In":[27,147],"most":[28],"cases,":[29],"used":[31,100,119],"technique":[32],"is":[33,80,99,118,135,141],"heavily":[34],"dependent":[35],"on":[36,205],"use":[38,153],"case":[39],"scenario":[40],"other":[42,113],"attributes,":[43],"e.g.":[44],"environment.":[46],"Both":[47],"approaches":[48],"their":[50],"own":[51],"advantages,":[52],"for":[53],"example,":[54],"sample":[55,192],"efficiency":[56],"computational":[58],"efficiency.":[59,193],"However,":[60],"when":[61],"combining":[62],"two,":[64],"advantages":[66],"of":[67,83,107,154,197],"each":[68],"can":[69,166],"be":[70],"combined":[71],"and":[72,189,208],"hence":[73],"achieve":[74],"better":[75],"performance.":[76],"The":[77],"TD-MPC":[78,160],"framework":[79],"an":[81],"example":[82],"this":[84,148],"approach.":[85],"On":[86,111],"hand,":[89,114],"a":[90,103,115,122,131,155,182],"world":[91],"model":[92,96],"combination":[94],"with":[95],"predictive":[97],"control":[98],"get":[102],"good":[104,123],"initial":[105],"estimate":[106],"value":[109],"function.":[110],"Q":[116],"function":[117,157],"provide":[121],"long-term":[124],"estimate.":[125],"Similar":[126],"algorithms":[128],"like":[129],"MuZero":[130],"latent":[132],"state":[133,174],"representation":[134],"used,":[136],"where":[137],"only":[138],"task-relevant":[139],"information":[140],"encoded":[142],"reduce":[144],"complexity.":[146],"paper,":[149],"propose":[151],"reconstruction":[156],"within":[158],"framework,":[161],"so":[162],"agent":[165,179],"reconstruct":[167],"original":[169],"observation":[170],"given":[171],"internal":[173],"representation.":[175],"This":[176],"allows":[177],"our":[178],"more":[183],"stable":[184],"signal":[186],"during":[187],"training":[188],"also":[190],"improves":[191],"Our":[194],"proposed":[195],"addition":[196],"another":[198],"loss":[199],"term":[200],"leads":[201],"improved":[203],"performance":[204],"both":[206],"state-":[207],"image-based":[209],"tasks":[210],"from":[211],"DeepMind-Control":[213],"suite.":[214]},"counts_by_year":[],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2023-04-19T00:00:00"}