{"id":"https://openalex.org/W7148690169","doi":"https://doi.org/10.48550/arxiv.2604.02151","title":"Auction-Based Online Policy Adaptation for Evolving Objectives","display_name":"Auction-Based Online Policy Adaptation for Evolving Objectives","publication_year":2026,"publication_date":"2026-04-02","ids":{"openalex":"https://openalex.org/W7148690169","doi":"https://doi.org/10.48550/arxiv.2604.02151"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2604.02151","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.02151","pdf_url":"https://arxiv.org/pdf/2604.02151","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/2604.02151","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133034857","display_name":"Guruprerana Shabadi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shabadi, Guruprerana","raw_affiliation_strings":["University of Pennsylvania , United States,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania , United States,","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081483854","display_name":"Kaushik Mallik","orcid":"https://orcid.org/0000-0001-9864-7475","observed_orcids":["https://orcid.org/0000-0001-9864-7475"]},"institutions":[{"id":"https://openalex.org/I4210162154","display_name":"IMDEA Software Institute","ror":"https://ror.org/04xvfkh51","country_code":"ES","type":"facility","lineage":["https://openalex.org/I105140100","https://openalex.org/I4210162154"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Mallik, Kaushik","raw_affiliation_strings":["IMDEA Software Institute , Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IMDEA Software Institute , Spain","institution_ids":["https://openalex.org/I4210162154"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":0.9994999766349792,"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":0.9994999766349792,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.0,"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/multi-objective-reinforcement-learning","display_name":"multi-objective reinforcement learning","score":0.9240000247955322},{"id":"https://openalex.org/keywords/auction-mechanisms","display_name":"auction mechanisms","score":0.8330000042915344},{"id":"https://openalex.org/keywords/reachability-objectives","display_name":"reachability objectives","score":0.6850000023841858},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.9179999828338623},{"id":"https://openalex.org/keywords/bidding-strategy","display_name":"bidding strategy","score":0.4749999940395355},{"id":"https://openalex.org/keywords/atari-games","display_name":"Atari games","score":0.7519999742507935}],"concepts":[{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6973000168800354},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6924999952316284},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6915000081062317},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6554999947547913},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6028000116348267},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5656999945640564},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.48350000381469727},{"id":"https://openalex.org/C136643341","wikidata":"https://www.wikidata.org/wiki/Q1361526","display_name":"Reachability","level":2,"score":0.4575999975204468},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.4097000062465668},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.30090001225471497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29989999532699585},{"id":"https://openalex.org/C52970973","wikidata":"https://www.wikidata.org/wiki/Q2497134","display_name":"Adaptive system","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.26980000734329224},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.25850000977516174},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.2533999979496002},{"id":"https://openalex.org/C8505890","wikidata":"https://www.wikidata.org/wiki/Q605095","display_name":"Budget constraint","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2604.02151","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.02151","pdf_url":"https://arxiv.org/pdf/2604.02151","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2604.02151","doi":"https://doi.org/10.48550/arxiv.2604.02151","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.02151","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2604.02151","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.02151","pdf_url":"https://arxiv.org/pdf/2604.02151","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7148690169.pdf","grobid_xml":"https://content.openalex.org/works/W7148690169.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W2736601468","https://openalex.org/W4399657258","https://openalex.org/W4416618409"],"related_works":["https://openalex.org/W2897714018","https://openalex.org/W2969489701","https://openalex.org/W4401024796","https://openalex.org/W2404716917","https://openalex.org/W1998649829","https://openalex.org/W6889799203","https://openalex.org/W2189549406","https://openalex.org/W7196968212","https://openalex.org/W7124273380","https://openalex.org/W7166706190"],"abstract_inverted_index":{"We":[0,152,251],"consider":[1],"multi-objective":[2],"reinforcement":[3],"learning":[4],"problems":[5],"where":[6,58,171,223],"objectives":[7,20,47,117,132,234],"come":[8],"from":[9,134],"an":[10],"identical":[11,138],"family":[12],"--":[13,21],"such":[14],"as":[15,42,131],"the":[16,43,80,89,92,99,112,119,127,135,155,164,172,198,218,231,241],"class":[17],"of":[18,45,91,140,200,220],"reachability":[19],"and":[22,68,104,203,230,257],"may":[23],"appear":[24],"or":[25,125],"disappear":[26],"at":[27,150],"runtime.":[28,151],"Our":[29,265],"goal":[30],"is":[31,61,70],"to":[32,82,111,178,205,227],"design":[33],"adaptive":[34],"policies":[35,77,158,173,242,273],"that":[36,209],"can":[37,144,159],"efficiently":[38],"adjust":[39],"their":[40,84,180],"behaviors":[41],"set":[44],"active":[46],"changes.":[48],"To":[49,183],"solve":[50],"this":[51],"problem,":[52,115],"we":[53,216],"propose":[54],"a":[55,64,73,102,141,167,258],"modular":[56],"framework":[57],"each":[59,176,185],"objective":[60],"supported":[62],"by":[63,122,162],"selfish":[65,156],"local":[66,157],"policy,":[67],"coordination":[69],"achieved":[71],"through":[72],"novel":[74],"auction-based":[75],"mechanism:":[76],"bid":[78],"for":[79],"right":[81],"execute":[83],"actions,":[85],"with":[86,262,275],"bids":[87,208],"reflecting":[88],"urgency":[90],"current":[93],"state.":[94],"The":[95],"highest":[96],"bidder":[97],"selects":[98],"action,":[100],"enabling":[101],"dynamic":[103,263],"interpretable":[105],"trade-off":[106],"among":[107],"objectives.":[108,182],"Going":[109],"back":[110],"original":[113],"adaptation":[114,149],"when":[116],"change,":[118],"system":[120],"adapts":[121],"simply":[123],"adding":[124],"removing":[126],"corresponding":[128],"policies.":[129],"Moreover,":[130],"arise":[133],"same":[136],"family,":[137],"copies":[139],"parameterized":[142],"policy":[143,186,248],"be":[145,160],"deployed,":[146],"facilitating":[147],"immediate":[148],"show":[153],"how":[154],"computed":[161],"turning":[163],"problem":[165],"into":[166],"general-sum":[168],"Markov":[169],"game,":[170],"compete":[174],"against":[175],"other":[177,201],"fulfill":[179],"own":[181,192],"succeed,":[184],"must":[187],"not":[188],"only":[189],"optimize":[190],"its":[191],"objective,":[193],"but":[194],"also":[195],"reason":[196],"about":[197],"presence":[199],"goals":[202],"learn":[204],"produce":[206],"calibrated":[207],"reflect":[210],"relative":[211],"priority.":[212],"Under":[213],"mild":[214],"assumptions,":[215],"prove":[217],"existence":[219],"Nash":[221],"equilibria":[222],"dishonest":[224],"bidding":[225],"leads":[226],"suboptimal":[228],"outcome,":[229],"most":[232],"urgent":[233],"win":[235],"control":[236],"automatically.":[237],"In":[238],"our":[239],"implementation,":[240],"are":[243],"trained":[244,274],"concurrently":[245],"using":[246],"proximal":[247],"optimization":[249],"(PPO).":[250],"evaluate":[252],"on":[253],"two":[254],"Atari":[255],"games":[256],"gridworld-based":[259],"path-planning":[260],"task":[261],"targets.":[264],"method":[266],"achieves":[267],"substantially":[268],"better":[269],"performance":[270],"than":[271],"monolithic":[272],"PPO.":[276]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-04-04T00:00:00"}