{"id":"https://openalex.org/W4394699099","doi":"https://doi.org/10.1109/tnnls.2024.3382985","title":"Decision-Making With Speculative Opponent Models","display_name":"Decision-Making With Speculative Opponent Models","publication_year":2024,"publication_date":"2024-04-10","ids":{"openalex":"https://openalex.org/W4394699099","doi":"https://doi.org/10.1109/tnnls.2024.3382985","pmid":"https://pubmed.ncbi.nlm.nih.gov/38598396"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2024.3382985","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3382985","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5103038422","display_name":"Jing Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Jing Sun","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100366855","display_name":"Shuo Chen","orcid":"https://orcid.org/0000-0002-0257-1240"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4392738278","display_name":"Beijing Institute for General Artificial Intelligence","ror":"https://ror.org/02kw1ws04","country_code":null,"type":"facility","lineage":["https://openalex.org/I4392738278"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Chen","raw_affiliation_strings":["Beijing Institute for General Artificial Intelligence, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute for General Artificial Intelligence, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4392738278"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438393","display_name":"Cong Zhang","orcid":"https://orcid.org/0000-0002-8434-1181"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Cong Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081047744","display_name":"Yining Ma","orcid":"https://orcid.org/0000-0002-6639-8547"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yining Ma","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100753720","display_name":"Jie Zhang","orcid":"https://orcid.org/0000-0002-1078-1766"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jie Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103038422"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":0.3626,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.62217666,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"36","issue":"3","first_page":"5304","last_page":"5318"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9975000023841858,"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":0.9975000023841858,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.9930999875068665,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.984499990940094,"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/adversary","display_name":"Adversary","score":0.5077379941940308},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.45322853326797485},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.1090472936630249}],"concepts":[{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.5077379941940308},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45322853326797485},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.1090472936630249}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2024.3382985","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3382985","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:38598396","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38598396","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8399999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":79,"referenced_works":["https://openalex.org/W1542941925","https://openalex.org/W1965555277","https://openalex.org/W2617547828","https://openalex.org/W2626637010","https://openalex.org/W2758442112","https://openalex.org/W2765302304","https://openalex.org/W2946045694","https://openalex.org/W2965433979","https://openalex.org/W2981038142","https://openalex.org/W2998802444","https://openalex.org/W2999778183","https://openalex.org/W3035478219","https://openalex.org/W3046288222","https://openalex.org/W3083927356","https://openalex.org/W3156295478","https://openalex.org/W3162079807","https://openalex.org/W4214717370","https://openalex.org/W4241996101","https://openalex.org/W4287756582","https://openalex.org/W4287757834","https://openalex.org/W4287810981","https://openalex.org/W4288594419","https://openalex.org/W4289258965","https://openalex.org/W4295150809","https://openalex.org/W4296437227","https://openalex.org/W4312458615","https://openalex.org/W4320341798","https://openalex.org/W4320843424","https://openalex.org/W4322729780","https://openalex.org/W4380558285","https://openalex.org/W6631190155","https://openalex.org/W6675811377","https://openalex.org/W6683195989","https://openalex.org/W6683204974","https://openalex.org/W6683300800","https://openalex.org/W6684205842","https://openalex.org/W6692846177","https://openalex.org/W6721101288","https://openalex.org/W6738796088","https://openalex.org/W6738860353","https://openalex.org/W6739516088","https://openalex.org/W6744562401","https://openalex.org/W6747146101","https://openalex.org/W6748203849","https://openalex.org/W6748910126","https://openalex.org/W6749304979","https://openalex.org/W6750645735","https://openalex.org/W6751420435","https://openalex.org/W6751629939","https://openalex.org/W6751912414","https://openalex.org/W6754407519","https://openalex.org/W6755069753","https://openalex.org/W6755224613","https://openalex.org/W6756040250","https://openalex.org/W6758507868","https://openalex.org/W6758683734","https://openalex.org/W6758846586","https://openalex.org/W6762491519","https://openalex.org/W6763153117","https://openalex.org/W6763173777","https://openalex.org/W6771274123","https://openalex.org/W6772452015","https://openalex.org/W6773097889","https://openalex.org/W6773161478","https://openalex.org/W6779594309","https://openalex.org/W6780575998","https://openalex.org/W6781750019","https://openalex.org/W6783055029","https://openalex.org/W6783196708","https://openalex.org/W6784341771","https://openalex.org/W6788735329","https://openalex.org/W6791043475","https://openalex.org/W6796436736","https://openalex.org/W6798374801","https://openalex.org/W6803581605","https://openalex.org/W6838369681","https://openalex.org/W6840380725","https://openalex.org/W6849080615","https://openalex.org/W6853876243"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4388150944","https://openalex.org/W4242235492","https://openalex.org/W2390279801","https://openalex.org/W4237162029","https://openalex.org/W2367268135","https://openalex.org/W4391913857","https://openalex.org/W2358668433"],"abstract_inverted_index":{"Opponent":[0],"modeling":[1,63],"has":[2],"proven":[3],"effective":[4],"in":[5],"enhancing":[6],"the":[7,10,27,59,72,80,87,90,97,112,116,125,133,136,141,154,168],"decision-making":[8],"of":[9,16,31,115,124,135],"controlled":[11,73],"agent":[12],"by":[13],"constructing":[14],"models":[15,94,109,139,181],"opponent":[17,62,93,138,156],"agents.":[18],"However,":[19],"existing":[20],"methods":[21,191],"often":[22],"rely":[23],"on":[24,68],"access":[25],"to":[26,46],"observations":[28],"and":[29,77,171,184],"actions":[30,99],"opponents,":[32],"a":[33,83,120,149,193],"requirement":[34],"that":[35,65,95,110,140,177],"is":[36,41],"infeasible":[37],"when":[38],"such":[39],"information":[40,70],"either":[42],"unobservable":[43],"or":[44],"challenging":[45,163],"obtain.":[47],"To":[48],"address":[49],"this":[50],"issue,":[51],"we":[52,146],"introduce":[53],"distributional":[54,107],"opponent-aided":[55],"multiagent":[56,164,173],"actor-critic":[57],"(DOMAC),":[58],"first":[60],"speculative":[61,92,137],"algorithm":[64],"relies":[66],"solely":[67],"local":[69,102],"(i.e.,":[71],"agent's":[74],"observations,":[75],"actions,":[76],"rewards).":[78],"Specifically,":[79],"actor":[81,142],"maintains":[82],"speculated":[84],"belief":[85],"about":[86],"opponents":[88],"using":[89,100],"tailored":[91],"predict":[96],"opponents'":[98,182],"only":[101],"information.":[103],"Moreover,":[104],"DOMAC":[105,179],"features":[106],"critic":[108],"estimate":[111],"return":[113],"distribution":[114],"actor's":[117,126],"policy,":[118],"yielding":[119],"more":[121,130],"fine-grained":[122],"assessment":[123],"quality.":[127],"This":[128],"thus":[129],"effectively":[131],"guides":[132],"training":[134],"depends":[143],"upon.":[144],"Furthermore,":[145],"formally":[147],"derive":[148],"policy":[150],"gradient":[151],"theorem":[152],"with":[153,192],"proposed":[155],"models.":[157],"Extensive":[158],"experiments":[159],"under":[160],"eight":[161],"different":[162],"benchmark":[165],"tasks":[166],"within":[167],"MPE,":[169],"Pommerman,":[170],"starcraft":[172],"challenge":[174],"(SMAC)":[175],"demonstrate":[176],"our":[178],"successfully":[180],"behaviors":[183],"delivers":[185],"superior":[186],"performance":[187],"against":[188],"state-of-the-art":[189],"(SOTA)":[190],"faster":[194],"convergence":[195],"speed.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}