{"id":"https://openalex.org/W4381167788","doi":"https://doi.org/10.1177/02783649231182453","title":"Online and offline learning of player objectives from partial observations in dynamic games","display_name":"Online and offline learning of player objectives from partial observations in dynamic games","publication_year":2023,"publication_date":"2023-06-18","ids":{"openalex":"https://openalex.org/W4381167788","doi":"https://doi.org/10.1177/02783649231182453"},"language":"en","primary_location":{"id":"doi:10.1177/02783649231182453","is_oa":true,"landing_page_url":"https://doi.org/10.1177/02783649231182453","pdf_url":"https://journals.sagepub.com/doi/pdf/10.1177/02783649231182453","source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://journals.sagepub.com/doi/pdf/10.1177/02783649231182453","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013374431","display_name":"Lasse Peters","orcid":"https://orcid.org/0000-0001-9008-7127"},"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"]},{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["DE","NL"],"is_corresponding":true,"raw_author_name":"Lasse Peters","raw_affiliation_strings":["Department for Photogrammetry, University of Bonn, Bonn, Germany","Department of Cognitive Robotic, Delft University of Technology, Delft, Netherlands"],"raw_orcid":"https://orcid.org/0000-0001-9008-7127","affiliations":[{"raw_affiliation_string":"Department for Photogrammetry, University of Bonn, Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]},{"raw_affiliation_string":"Department of Cognitive Robotic, Delft University of Technology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009308827","display_name":"Vicen\u00e7 Rubies-Royo","orcid":"https://orcid.org/0000-0002-8814-0248"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vicen\u00e7 Rubies-Royo","raw_affiliation_strings":["University of California Berkeley, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045155646","display_name":"Claire J. Tomlin","orcid":"https://orcid.org/0000-0003-3192-3185"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Claire J Tomlin","raw_affiliation_strings":["University of California Berkeley, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029788290","display_name":"Laura Ferranti","orcid":"https://orcid.org/0000-0003-3856-6221"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Laura Ferranti","raw_affiliation_strings":["Department of Cognitive Robotic, Delft University of Technology, Delft, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Cognitive Robotic, Delft University of Technology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013297671","display_name":"Javier Alonso\u2013Mora","orcid":"https://orcid.org/0000-0003-0058-570X"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Javier Alonso-Mora","raw_affiliation_strings":["Department of Cognitive Robotic, Delft University of Technology, Delft, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Cognitive Robotic, Delft University of Technology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011166267","display_name":"Cyrill Stachniss","orcid":"https://orcid.org/0000-0003-1173-6972"},"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":"Cyrill Stachniss","raw_affiliation_strings":["Department for Photogrammetry, University of Bonn, Bonn, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department for Photogrammetry, University of Bonn, Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070827615","display_name":"David Fridovich-Keil","orcid":"https://orcid.org/0000-0002-5866-6441"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Fridovich-Keil","raw_affiliation_strings":["The University of Texas at Austin, Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5013374431"],"corresponding_institution_ids":["https://openalex.org/I135140700","https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":1.0487,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.73263199,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"42","issue":"10","first_page":"917","last_page":"937"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9958999752998352,"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/T10524","display_name":"Traffic control and management","score":0.9958999752998352,"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":0.993399977684021,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9900000095367432,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/computer-science","display_name":"Computer science","score":0.7205379009246826},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5821213126182556},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.565866231918335},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5602951645851135},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.5242077112197876},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.517194390296936},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49523916840553284},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4839751720428467},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4791395366191864},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47344064712524414},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.457424521446228},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.43573033809661865},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3277025818824768},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13889473676681519},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.1231909692287445},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.11999991536140442},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11921223998069763}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7205379009246826},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5821213126182556},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.565866231918335},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5602951645851135},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.5242077112197876},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.517194390296936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49523916840553284},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4839751720428467},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4791395366191864},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47344064712524414},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.457424521446228},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.43573033809661865},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3277025818824768},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13889473676681519},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.1231909692287445},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.11999991536140442},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11921223998069763},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1177/02783649231182453","is_oa":true,"landing_page_url":"https://doi.org/10.1177/02783649231182453","pdf_url":"https://journals.sagepub.com/doi/pdf/10.1177/02783649231182453","source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","raw_type":"journal-article"},{"id":"pmh:oai:tudelft.nl:uuid:f4dd7063-b31e-4edf-aeb7-25db6861cc0e","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:f4dd7063-b31e-4edf-aeb7-25db6861cc0e","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.1177/02783649231182453","is_oa":true,"landing_page_url":"https://doi.org/10.1177/02783649231182453","pdf_url":"https://journals.sagepub.com/doi/pdf/10.1177/02783649231182453","source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4381167788.pdf"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1512520166","https://openalex.org/W1918816242","https://openalex.org/W1970101292","https://openalex.org/W1970916399","https://openalex.org/W2001024683","https://openalex.org/W2002373723","https://openalex.org/W2019901401","https://openalex.org/W2037997802","https://openalex.org/W2107308405","https://openalex.org/W2120575449","https://openalex.org/W2123871098","https://openalex.org/W2124394479","https://openalex.org/W2227909145","https://openalex.org/W2737702598","https://openalex.org/W2765116338","https://openalex.org/W2765199760","https://openalex.org/W2808171692","https://openalex.org/W2842089854","https://openalex.org/W2884371529","https://openalex.org/W2911825241","https://openalex.org/W2982117252","https://openalex.org/W2996499288","https://openalex.org/W3012421647","https://openalex.org/W3022321359","https://openalex.org/W3045019238","https://openalex.org/W3046169940","https://openalex.org/W3081754649","https://openalex.org/W3089576059","https://openalex.org/W3098632684","https://openalex.org/W3105558219","https://openalex.org/W3120436098","https://openalex.org/W3153199159","https://openalex.org/W3159797474","https://openalex.org/W3174761862","https://openalex.org/W3214632212","https://openalex.org/W4231147659","https://openalex.org/W4255052368","https://openalex.org/W4255867308","https://openalex.org/W4302033101"],"related_works":["https://openalex.org/W4388311650","https://openalex.org/W4362501864","https://openalex.org/W1974056099","https://openalex.org/W4306904969","https://openalex.org/W4312141693","https://openalex.org/W1536009559","https://openalex.org/W1969185016","https://openalex.org/W2103821767","https://openalex.org/W2111030377","https://openalex.org/W2037619003"],"abstract_inverted_index":{"Robots":[0],"deployed":[1],"to":[2,9,121],"the":[3,88],"real":[4],"world":[5],"must":[6],"be":[7],"able":[8],"interact":[10],"with":[11,97,113],"other":[12],"agents":[13,30],"in":[14,28,73,127,135,140],"their":[15],"environment.":[16],"Dynamic":[17],"game":[18],"theory":[19],"provides":[20],"a":[21,40,50,66],"powerful":[22],"mathematical":[23],"framework":[24],"for":[25,69],"modeling":[26],"scenarios":[27,139],"which":[29,141],"have":[31],"individual":[32],"objectives":[33,72,85],"and":[34,102,125,151],"interactions":[35],"evolve":[36],"over":[37],"time.":[38],"However,":[39],"key":[41],"limitation":[42],"of":[43,53,90,94,99],"such":[44],"techniques":[45],"is":[46,119],"that":[47,156,166],"they":[48],"require":[49],"priori":[51],"knowledge":[52],"all":[54],"players\u2019":[55,71,144],"objectives.":[56],"In":[57],"this":[58,62],"work,":[59],"we":[60,142],"address":[61],"issue":[63],"by":[64,86],"proposing":[65],"novel":[67],"method":[68,134,158],"learning":[70,124],"continuous":[74],"dynamic":[75],"games":[76],"from":[77,163],"noise-corrupted,":[78],"partial":[79],"state":[80,111,115],"observations.":[81],"Our":[82],"approach":[83,118],"learns":[84],"coupling":[87,109],"estimation":[89],"unknown":[91],"cost":[92],"parameters":[93],"each":[95],"player":[96],"inference":[98],"unobserved":[100],"states":[101],"inputs":[103],"through":[104],"Nash":[105],"equilibrium":[106],"constraints.":[107],"By":[108],"past":[110],"estimates":[112,160],"future":[114],"predictions,":[116],"our":[117,133,157],"amenable":[120],"simultaneous":[122],"online":[123],"prediction":[126],"receding":[128],"horizon":[129],"fashion.":[130],"We":[131],"demonstrate":[132],"several":[136],"simulated":[137],"traffic":[138],"recover":[143],"preferences,":[145],"for,":[146],"e.g.":[147],"desired":[148],"travel":[149],"speed":[150],"collision-avoidance":[152],"behavior.":[153],"Results":[154],"show":[155],"reliably":[159],"game-theoretic":[161],"models":[162],"noise-corrupted":[164],"data":[165],"closely":[167],"matches":[168],"ground-truth":[169],"objectives,":[170],"consistently":[171],"outperforming":[172],"state-of-the-art":[173],"approaches.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}
