{"id":"https://openalex.org/W7123347780","doi":"https://doi.org/10.1109/cdc57313.2025.11312127","title":"Principled Learning-to-Communicate with Quasi-Classical Information Structures","display_name":"Principled Learning-to-Communicate with Quasi-Classical Information Structures","alternate_titles":[],"publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W7123347780","doi":"https://doi.org/10.1109/cdc57313.2025.11312127"},"language":"en","primary_location":{"id":"doi:10.1109/cdc57313.2025.11312127","doi":"https://doi.org/10.1109/cdc57313.2025.11312127","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312127","pdf_url":null,"source":{"id":"https://openalex.org/S4210221977","display_name":"IEEE Conference on Decision and Control (CDC)","issn_l":"0191-2216","issn":["0191-2216"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W7123347780"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"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/A5122874658","display_name":"Xiangyu Liu","orcid":"https://orcid.org/0009-0004-1903-9789","observed_orcids":["https://orcid.org/0009-0004-1903-9789"]},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiangyu Liu","raw_affiliation_strings":["University of Maryland,College Park,MD,USA,20742"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,MD,USA,20742","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030508108","display_name":"Haoyi You","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haoyi You","raw_affiliation_strings":["University of Maryland,College Park,MD,USA,20742"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,MD,USA,20742","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047410441","display_name":"Kaiqing Zhang","orcid":"https://orcid.org/0000-0002-7446-7581","observed_orcids":["https://orcid.org/0000-0002-7446-7581"]},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaiqing Zhang","raw_affiliation_strings":["University of Maryland,College Park,MD,USA,20742"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,MD,USA,20742","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6189","last_page":"6194"},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9707000255584717,"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":0.9707000255584717,"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/T11031","display_name":"Game Theory and Applications","score":0.014299999922513962,"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"}},{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.0032999999821186066,"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/learning-to-communicate","display_name":"learning to communicate","score":0.9779999852180481},{"id":"https://openalex.org/keywords/information-structure","display_name":"information structure","score":0.8069999814033508},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-processes","display_name":"partially observable Markov decision processes","score":0.8629999756813049},{"id":"https://openalex.org/keywords/decentralized-stochastic-control","display_name":"decentralized stochastic control","score":0.7599999904632568},{"id":"https://openalex.org/keywords/common-information","display_name":"common information","score":0.8920000195503235},{"id":"https://openalex.org/keywords/multi-agent-reinforcement-learning","display_name":"multi-agent reinforcement learning","score":0.8339999914169312},{"id":"https://openalex.org/keywords/computational-hardness","display_name":"computational hardness","score":0.7680000066757202},{"id":"https://openalex.org/keywords/quasi-polynomial-time-algorithms","display_name":"quasi-polynomial time algorithms","score":0.7480000257492065},{"id":"https://openalex.org/keywords/decentralized-planning","display_name":"decentralized planning","score":0.5680000185966492}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6858000159263611},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.6083999872207642},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.5896000266075134},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5719000101089478},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5554999709129333},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5094000101089478},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5092999935150146},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5023000240325928},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4839000105857849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.435699999332428},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4228000044822693},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.41600000858306885},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.3303999900817871},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.31529998779296875},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C52622258","wikidata":"https://www.wikidata.org/wiki/Q131222","display_name":"Information theory","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26750001311302185},{"id":"https://openalex.org/C205875254","wikidata":"https://www.wikidata.org/wiki/Q17156857","display_name":"Decentralised system","level":3,"score":0.25690001249313354},{"id":"https://openalex.org/C115988155","wikidata":"https://www.wikidata.org/wiki/Q3262192","display_name":"Decision problem","level":2,"score":0.25619998574256897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc57313.2025.11312127","doi":"https://doi.org/10.1109/cdc57313.2025.11312127","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312127","pdf_url":null,"source":{"id":"https://openalex.org/S4210221977","display_name":"IEEE Conference on Decision and Control (CDC)","issn_l":"0191-2216","issn":["0191-2216"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320316514","display_name":"Arm","ror":"https://ror.org/04mmhzs81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W200491663","https://openalex.org/W1514791329","https://openalex.org/W1932883063","https://openalex.org/W1991888757","https://openalex.org/W2032100464","https://openalex.org/W2076110408","https://openalex.org/W2088956500","https://openalex.org/W2113231618","https://openalex.org/W2115118348","https://openalex.org/W2121154010","https://openalex.org/W2123827275","https://openalex.org/W2138966161","https://openalex.org/W2156216606","https://openalex.org/W2395575420","https://openalex.org/W2402402867","https://openalex.org/W2498386205","https://openalex.org/W2803155336","https://openalex.org/W4315472290","https://openalex.org/W4376639681","https://openalex.org/W4394586261","https://openalex.org/W4399833126"],"related_works":["https://openalex.org/W7135188524","https://openalex.org/W4388903833","https://openalex.org/W7008615907","https://openalex.org/W7099578658","https://openalex.org/W2524491825","https://openalex.org/W7221777919","https://openalex.org/W1545451257","https://openalex.org/W2049306799","https://openalex.org/W3094572571","https://openalex.org/W7162022847"],"abstract_inverted_index":{"Learning-to-Communicate":[0],"(LTC)":[1],"in":[2,12,38,72,109,134],"partially":[3,74],"observable":[4,75],"environments":[5],"has":[6,34],"emerged":[7],"and":[8,20,48,88,111,141,147,165,179],"received":[9],"increasing":[10],"attention":[11],"deep":[13],"multi-agent":[14],"reinforcement":[15],"learning,":[16],"where":[17],"the":[18,27,30,60,81,94,156,168,180,201],"control":[19,39],"communication":[21,33],"strategies":[22],"are":[23,106],"jointly":[24],"learned.":[25],"On":[26],"other":[28],"hand,":[29],"impact":[31],"of":[32,57,62,123,152,182,207],"been":[35],"extensively":[36],"studied":[37],"theory.":[40],"In":[41],"this":[42,67],"paper,":[43],"we":[44,69,137,170],"seek":[45],"to":[46],"formalize":[47,70],"better":[49],"understand":[50],"LTC":[51,71,90],"by":[52],"bridging":[53],"these":[54],"two":[55],"lines":[56],"work,":[58],"through":[59],"lens":[61],"information":[63,98],"structures":[64],"(ISs).":[65],"To":[66],"end,":[68],"decentralized":[73,85],"Markov":[76],"decision":[77],"processes":[78],"(Dec-POMDPs)":[79],"under":[80],"common-information-based":[82,185],"framework":[83],"from":[84],"stochastic":[86],"control,":[87],"classify":[89],"problems":[91],"based":[92],"on":[93,114],"ISs":[95],"before":[96],"(additional)":[97],"sharing.":[99],"We":[100,118],"first":[101],"show":[102,148],"that":[103,149],"non-classical":[104],"LTCs":[105,154],"computationally":[107,194],"intractable":[108,195],"general,":[110],"thus":[112],"focus":[113],"quasi-classical":[115],"(QC)":[116],"LTCs.":[117],"then":[119],"propose":[120],"a":[121],"series":[122],"conditions":[124,158],"for":[125,144],"QC":[126,145,153,177],"LTCs,":[127,146],"violating":[128],"which":[129,204],"can":[130,159],"cause":[131],"computational":[132],"hardness":[133],"general.":[135],"Further,":[136],"develop":[138],"provable":[139],"planning":[140],"learning":[142],"algorithms":[143],"some":[150,173],"examples":[151],"satisfying":[155],"above":[157],"be":[160,206],"solved":[161],"with":[162,200],"quasi-polynomial":[163],"time":[164],"samples.":[166],"Along":[167],"way,":[169],"also":[171],"establish":[172],"relationship":[174],"between":[175],"(strictly)":[176],"IS":[178],"condition":[181],"having":[183],"strategy-independent":[184],"beliefs":[186],"(SI-CIBs),":[187],"as":[188,190],"well":[189],"solving":[191],"Dec-POMDPs":[192],"without":[193],"oracles":[196],"but":[197],"beyond":[198],"those":[199],"SI-CIB":[202],"condition,":[203],"may":[205],"independent":[208],"interest.":[209]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W7123347780","counts_by_year":[],"updated_date":"2026-11-16T12:05:36.265796","created_date":"2026-01-14T00:00:00"}
