{"id":"https://openalex.org/W4402302738","doi":"https://doi.org/10.1109/tpami.2024.3455257","title":"Diversifying Policies With Non-Markov Dispersion to Expand the Solution Space","display_name":"Diversifying Policies With Non-Markov Dispersion to Expand the Solution Space","publication_year":2024,"publication_date":"2024-09-06","ids":{"openalex":"https://openalex.org/W4402302738","doi":"https://doi.org/10.1109/tpami.2024.3455257","pmid":"https://pubmed.ncbi.nlm.nih.gov/39240734"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3455257","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3455257","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","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/A5078253656","display_name":"Bohao Qu","orcid":"https://orcid.org/0000-0003-3192-8736"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bohao Qu","raw_affiliation_strings":["School of Artificial Intelligence, Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, Ministry of Education, Jilin University, Changchun, Jilin, China","School of Artificial Intelligence, Jilin University, Changchun, Jilin, China"],"raw_orcid":"https://orcid.org/0000-0003-3192-8736","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, Ministry of Education, Jilin University, Changchun, Jilin, China","institution_ids":["https://openalex.org/I194450716"]},{"raw_affiliation_string":"School of Artificial Intelligence, Jilin University, Changchun, Jilin, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043782065","display_name":"Xiaofeng Cao","orcid":"https://orcid.org/0000-0002-7391-0334"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Cao","raw_affiliation_strings":["School of Artificial Intelligence, Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, Ministry of Education, Jilin University, Changchun, Jilin, China","School of Artificial Intelligence, Jilin University, Changchun, Jilin, China"],"raw_orcid":"https://orcid.org/0000-0002-7391-0334","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, Ministry of Education, Jilin University, Changchun, Jilin, China","institution_ids":["https://openalex.org/I194450716"]},{"raw_affiliation_string":"School of Artificial Intelligence, Jilin University, Changchun, Jilin, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029392006","display_name":"Yi Chang","orcid":"https://orcid.org/0000-0003-2697-8093"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Chang","raw_affiliation_strings":["School of Artificial Intelligence, Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, Ministry of Education, Jilin University, Changchun, Jilin, China","School of Artificial Intelligence, Jilin University, Changchun, Jilin, China"],"raw_orcid":"https://orcid.org/0000-0003-2697-8093","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, Ministry of Education, Jilin University, Changchun, Jilin, China","institution_ids":["https://openalex.org/I194450716"]},{"raw_affiliation_string":"School of Artificial Intelligence, Jilin University, Changchun, Jilin, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021751767","display_name":"Ivor W. Tsang","orcid":"https://orcid.org/0000-0001-8095-4637"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ivor W. Tsang","raw_affiliation_strings":["Institute of High Performance Computing (IHPC) and Centre for Frontier AI Research (CFAR), Agency for Science, Technology and Research, A*STAR, Singapore","Institute of High Performance Computing (IHPC) and Centre for Frontier AI Research (CFAR), Agency for Science, Technology and Research (A*STAR), Singapore"],"raw_orcid":"https://orcid.org/0000-0001-8095-4637","affiliations":[{"raw_affiliation_string":"Institute of High Performance Computing (IHPC) and Centre for Frontier AI Research (CFAR), Agency for Science, Technology and Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3004594783"]},{"raw_affiliation_string":"Institute of High Performance Computing (IHPC) and Centre for Frontier AI Research (CFAR), Agency for Science, Technology and Research (A*STAR), Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3004594783"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068243197","display_name":"Yew-Soon Ong","orcid":"https://orcid.org/0000-0002-4480-169X"},"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":"Yew-Soon Ong","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4480-169X","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.61,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.72508014,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"46","issue":"12","first_page":"11392","last_page":"11408"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13297","display_name":"History and advancements in chemistry","score":0.10920000076293945,"subfield":{"id":"https://openalex.org/subfields/1606","display_name":"Physical and Theoretical Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13297","display_name":"History and advancements in chemistry","score":0.10920000076293945,"subfield":{"id":"https://openalex.org/subfields/1606","display_name":"Physical and Theoretical Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11810","display_name":"Complex Systems and Decision Making","score":0.10769999772310257,"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/markov-process","display_name":"Markov process","score":0.5306906700134277},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5306516885757446},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5175482630729675},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5043658018112183},{"id":"https://openalex.org/keywords/dispersion","display_name":"Dispersion (optics)","score":0.4961887001991272},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47475293278694153},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3264075219631195},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27874240279197693},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2635127902030945},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2087550163269043},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11858871579170227},{"id":"https://openalex.org/keywords/optics","display_name":"Optics","score":0.09317949414253235}],"concepts":[{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5306906700134277},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5306516885757446},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5175482630729675},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5043658018112183},{"id":"https://openalex.org/C177562468","wikidata":"https://www.wikidata.org/wiki/Q182893","display_name":"Dispersion (optics)","level":2,"score":0.4961887001991272},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47475293278694153},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3264075219631195},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27874240279197693},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2635127902030945},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2087550163269043},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11858871579170227},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.09317949414253235},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2024.3455257","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3455257","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:39240734","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39240734","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 pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G1211044700","display_name":null,"funder_award_id":"U2341229","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1212804187","display_name":null,"funder_award_id":"62476109","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4000995272","display_name":null,"funder_award_id":"20240101373JC","funder_id":"https://openalex.org/F4320310121","funder_display_name":"Natural Science Foundation of Jilin Province"},{"id":"https://openalex.org/G6592930967","display_name":null,"funder_award_id":"2023YFF0905400","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6789821807","display_name":null,"funder_award_id":"62206108","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320310121","display_name":"Natural Science Foundation of Jilin Province","ror":null},{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320696","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09"},{"id":"https://openalex.org/F4320320766","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320325256","display_name":"Info-communications Media Development Authority","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":74,"referenced_works":["https://openalex.org/W1738827650","https://openalex.org/W1977655452","https://openalex.org/W2048984163","https://openalex.org/W2064675550","https://openalex.org/W2109910161","https://openalex.org/W2133180954","https://openalex.org/W2138779671","https://openalex.org/W2145339207","https://openalex.org/W2167117957","https://openalex.org/W2209913494","https://openalex.org/W2462548332","https://openalex.org/W2567705466","https://openalex.org/W2734058336","https://openalex.org/W2766447205","https://openalex.org/W2767257775","https://openalex.org/W2789027502","https://openalex.org/W2808386811","https://openalex.org/W2902907165","https://openalex.org/W2962687375","https://openalex.org/W2963390429","https://openalex.org/W2963542740","https://openalex.org/W2966128956","https://openalex.org/W2966174181","https://openalex.org/W2970673985","https://openalex.org/W2973229164","https://openalex.org/W2982316857","https://openalex.org/W2990747716","https://openalex.org/W2997022832","https://openalex.org/W3107153805","https://openalex.org/W3173218700","https://openalex.org/W4220775068","https://openalex.org/W4230075034","https://openalex.org/W4283815845","https://openalex.org/W4385245566","https://openalex.org/W6622219343","https://openalex.org/W6629985675","https://openalex.org/W6633322926","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6732573306","https://openalex.org/W6734678876","https://openalex.org/W6741002519","https://openalex.org/W6742667875","https://openalex.org/W6747092830","https://openalex.org/W6747473740","https://openalex.org/W6748203849","https://openalex.org/W6748398410","https://openalex.org/W6748594472","https://openalex.org/W6748603076","https://openalex.org/W6748839928","https://openalex.org/W6751912414","https://openalex.org/W6752298494","https://openalex.org/W6753311412","https://openalex.org/W6754905691","https://openalex.org/W6755133785","https://openalex.org/W6759440498","https://openalex.org/W6762477406","https://openalex.org/W6768831546","https://openalex.org/W6771739536","https://openalex.org/W6772005887","https://openalex.org/W6773329755","https://openalex.org/W6777641504","https://openalex.org/W6778920008","https://openalex.org/W6779390226","https://openalex.org/W6779461681","https://openalex.org/W6780559895","https://openalex.org/W6784517308","https://openalex.org/W6784862960","https://openalex.org/W6788735329","https://openalex.org/W6791915630","https://openalex.org/W6796814964","https://openalex.org/W6797349370","https://openalex.org/W6810855250","https://openalex.org/W6854151364"],"related_works":["https://openalex.org/W1660242800","https://openalex.org/W2077211377","https://openalex.org/W1006270037","https://openalex.org/W3152686072","https://openalex.org/W3129238073","https://openalex.org/W2379651310","https://openalex.org/W2113019827","https://openalex.org/W1541249122","https://openalex.org/W2413828414","https://openalex.org/W2367222340"],"abstract_inverted_index":{"Policy":[0],"diversity,":[1],"encompassing":[2],"the":[3,25,44,52,68,112,115,127,139,156,160,177,186,192,196,211,217,223,232,258,266],"variety":[4],"of":[5,59,70,114,141,203,239],"policies":[6,108,255],"an":[7,56],"agent":[8],"can":[9,220,250],"adopt,":[10],"enhances":[11],"reinforcement":[12],"learning":[13,268],"(RL)":[14],"success":[15],"by":[16,145],"fostering":[17],"more":[18,132,252,262],"robust,":[19],"adaptable,":[20],"and":[21,61,86,143,168,199,242],"innovative":[22],"problem-solving":[23],"in":[24,29,48,91,97,155,164,195],"environment.":[26],"The":[27,122],"environment":[28],"which":[30],"standard":[31],"RL":[32],"operates":[33],"is":[34,124,214],"usually":[35],"modeled":[36],"with":[37],"a":[38,65,146,182,201,228],"Markov":[39],"Decision":[40],"Process":[41],"(MDP)":[42],"as":[43,185],"theoretical":[45],"foundation.":[46],"However,":[47],"many":[49],"real-world":[50],"scenarios,":[51],"rewards":[53],"depend":[54],"on":[55],"agent's":[57],"history":[58],"states":[60,142],"actions":[62,144],"leading":[63],"to":[64,82,109,125,149,180,190],"non-MDP.":[66,173],"Under":[67],"premise":[69],"policy":[71,151,178,187,193,234],"diffusion":[72],"initialization,":[73],"non-MDPs":[74,106],"may":[75],"have":[76],"unstructured":[77],"expanding":[78,257],"solution":[79,117,128,157,197,259],"space":[80,118,198],"due":[81],"varying":[83],"historical":[84],"information":[85],"temporal":[87],"dependencies.":[88],"This":[89],"results":[90,238],"solutions":[92,104],"having":[93],"non-equivalent":[94],"closed":[95],"forms":[96],"non-MDPs.":[98],"In":[99],"this":[100,247],"paper,":[101],"deriving":[102],"diverse":[103,133,204,229,254],"for":[105,153,172,231],"requires":[107],"break":[110],"through":[111,119],"boundaries":[113],"current":[116],"gradual":[120],"dispersion.":[121],"goal":[123],"expand":[126],"space,":[129,158,260],"thereby":[130],"obtaining":[131],"policies.":[134,205],"Specifically,":[135],"we":[136,175,207],"first":[137],"model":[138],"sequences":[140],"transformer-based":[147],"method":[148],"learn":[150],"embeddings":[152,179,219],"dispersion":[154,183,194,212,248],"since":[159],"transformer":[161],"has":[162],"advantages":[163],"handling":[165],"sequential":[166],"data":[167],"capturing":[169],"long-range":[170],"dependencies":[171],"Then,":[174],"stack":[176],"construct":[181],"matrix":[184,213],"diversity":[188],"measure":[189],"induce":[191],"obtain":[200,251],"set":[202],"Finally,":[206],"prove":[208],"that":[209,246],"if":[210],"positive":[215],"definite,":[216],"dispersed":[218],"effectively":[221],"enlarge":[222],"disagreements":[224],"across":[225],"policies,":[226],"yielding":[227],"expression":[230],"original":[233],"embedding":[235],"distribution.":[236],"Experimental":[237],"both":[240],"non-MDP":[241],"MDP":[243],"environments":[244],"show":[245],"scheme":[249],"expressive":[253],"via":[256],"showing":[261],"robust":[263],"performance":[264],"than":[265],"recent":[267],"baselines.":[269]},"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"}