{"id":"https://openalex.org/W4407448900","doi":"https://doi.org/10.1109/tg.2025.3542158","title":"Leveraging Privileged Information for Partially Observable Reinforcement Learning","display_name":"Leveraging Privileged Information for Partially Observable Reinforcement Learning","publication_year":2025,"publication_date":"2025-02-13","ids":{"openalex":"https://openalex.org/W4407448900","doi":"https://doi.org/10.1109/tg.2025.3542158"},"language":"en","primary_location":{"id":"doi:10.1109/tg.2025.3542158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tg.2025.3542158","pdf_url":null,"source":{"id":"https://openalex.org/S4210224842","display_name":"IEEE Transactions on Games","issn_l":"2475-1502","issn":["2475-1502","2475-1510"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Games","raw_type":"journal-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":null,"display_name":"Jinqiu Li","orcid":"https://orcid.org/0009-0009-1308-098X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinqiu Li","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-1308-098X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055979604","display_name":"Enmin Zhao","orcid":"https://orcid.org/0000-0001-6117-5080"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Enmin Zhao","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tong Wei","orcid":"https://orcid.org/0009-0004-2048-0969"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Wei","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-2048-0969","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076090670","display_name":"Junliang Xing","orcid":"https://orcid.org/0000-0001-6801-0510"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junliang Xing","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6801-0510","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040673285","display_name":"Shiming Xiang","orcid":"https://orcid.org/0000-0002-2089-9733"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiming Xiang","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2089-9733","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5399,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.89169374,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"17","issue":"3","first_page":"765","last_page":"776"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.8952999711036682,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.8952999711036682,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8503999710083008,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7613805532455444},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.6843175888061523},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5555061101913452},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5449579358100891},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4199259877204895},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.33817124366760254},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.23950493335723877},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.1275545358657837},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11676299571990967}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7613805532455444},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.6843175888061523},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5555061101913452},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5449579358100891},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4199259877204895},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.33817124366760254},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.23950493335723877},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.1275545358657837},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11676299571990967},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tg.2025.3542158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tg.2025.3542158","pdf_url":null,"source":{"id":"https://openalex.org/S4210224842","display_name":"IEEE Transactions on Games","issn_l":"2475-1502","issn":["2475-1502","2475-1510"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Games","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G4257201797","display_name":null,"funder_award_id":"62222606","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2617547828","https://openalex.org/W2746553466","https://openalex.org/W2904675649","https://openalex.org/W2964198579","https://openalex.org/W2973229164","https://openalex.org/W2982316857","https://openalex.org/W2989847975","https://openalex.org/W2990747716","https://openalex.org/W2996896271","https://openalex.org/W3103837004","https://openalex.org/W3128855716","https://openalex.org/W3178094535","https://openalex.org/W4237844826","https://openalex.org/W4283801634","https://openalex.org/W4296474779","https://openalex.org/W4312279581","https://openalex.org/W4379058658","https://openalex.org/W4385338927","https://openalex.org/W4405734344","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W1994680671","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2000283393","https://openalex.org/W2920061524","https://openalex.org/W2002320543","https://openalex.org/W2040927204","https://openalex.org/W2061947244","https://openalex.org/W2150232912","https://openalex.org/W1977959518"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,10,75,120,135,142],"has":[2],"achieved":[3],"remarkable":[4],"success":[5],"across":[6],"diverse":[7],"scenarios.":[8],"However,":[9],"optimal":[11,138],"policies":[12,47,139],"within":[13,114],"partially":[14],"observable":[15],"games":[16],"remains":[17],"a":[18,93],"formidable":[19],"challenge.":[20],"Crucial":[21],"privileged":[22],"information":[23],"in":[24,62,155],"states":[25],"is":[26],"often":[27,59],"shrouded":[28],"during":[29,39],"gameplay,":[30],"yet":[31],"ideally,":[32],"it":[33],"should":[34],"be":[35],"accessible":[36],"and":[37,81,91,121,166,170],"exploitable":[38],"training.":[40],"Previous":[41],"studies":[42],"have":[43],"concentrated":[44],"on":[45,50],"formulating":[46],"based":[48],"wholly":[49],"partial":[51,79,125],"observations":[52,80],"or":[53],"oracle":[54,82,145],"states.":[55,83,146],"Nevertheless,":[56],"these":[57],"approaches":[58],"face":[60],"hindrances":[61],"attaining":[63],"effective":[64],"generalization.":[65],"To":[66],"surmount":[67],"this":[68,86],"challenge,":[69],"we":[70],"propose":[71],"the":[72,105,108,115,144,171],"actor\u2013cross-critic":[73],"(ACC)":[74],"framework,":[76,117],"integrating":[77],"both":[78],"ACC":[84,132],"achieves":[85],"by":[87],"coordinating":[88],"two":[89],"critics":[90],"invoking":[92],"maximization":[94],"operation":[95],"mechanism":[96],"to":[97],"switch":[98],"between":[99],"them":[100],"dynamically.":[101],"This":[102],"approach":[103],"encourages":[104],"selection":[106],"of":[107],"higher":[109],"values":[110],"when":[111],"computing":[112],"advantages":[113],"actor\u2013critic":[116,141],"thereby":[118],"accelerating":[119],"mitigating":[122],"bias":[123],"under":[124],"observability.":[126],"Some":[127],"theoretical":[128],"analyses":[129],"show":[130],"that":[131],"exhibits":[133],"better":[134],"ability":[136],"toward":[137],"than":[140],"using":[143],"We":[147],"highlight":[148],"its":[149],"superior":[150],"performance":[151],"through":[152],"comprehensive":[153],"evaluations":[154],"decision-making":[156],"tasks,":[157],"such":[158],"as":[159],"<italic":[160,163,167,175],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[161,164,168,176],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">QuestBall</i>,":[162],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Minigrid</i>,":[165],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Atari</i>,":[169],"challenging":[172],"card":[173],"game":[174],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">DouDizhu</i>.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}