{"id":"https://openalex.org/W4409426178","doi":"https://doi.org/10.1109/tetci.2025.3555250","title":"Improving Exploration in Deep Reinforcement Learning for Incomplete Information Competition Environments","display_name":"Improving Exploration in Deep Reinforcement Learning for Incomplete Information Competition Environments","publication_year":2025,"publication_date":"2025-04-14","ids":{"openalex":"https://openalex.org/W4409426178","doi":"https://doi.org/10.1109/tetci.2025.3555250"},"language":"en","primary_location":{"id":"doi:10.1109/tetci.2025.3555250","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetci.2025.3555250","pdf_url":null,"source":{"id":"https://openalex.org/S4210210251","display_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","issn_l":"2471-285X","issn":["2471-285X"],"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 Emerging Topics in Computational Intelligence","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":"https://openalex.org/A5070371129","display_name":"Jie Lin","orcid":"https://orcid.org/0000-0003-3476-110X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Lin","raw_affiliation_strings":["Xi&#x0027;an Jiaotong University, Xi&#x0027;an, China"],"raw_orcid":"https://orcid.org/0000-0003-3476-110X","affiliations":[{"raw_affiliation_string":"Xi&#x0027;an Jiaotong University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071915419","display_name":"Yuhao Ye","orcid":"https://orcid.org/0009-0009-3404-6668"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhao Ye","raw_affiliation_strings":["Xi&#x0027;an Jiaotong University, Xi&#x0027;an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi&#x0027;an Jiaotong University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shaobo Li","orcid":"https://orcid.org/0009-0003-8470-010X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaobo Li","raw_affiliation_strings":["Xi&#x0027;an Jiaotong University, Xi&#x0027;an, China"],"raw_orcid":"https://orcid.org/0009-0003-8470-010X","affiliations":[{"raw_affiliation_string":"Xi&#x0027;an Jiaotong University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101598769","display_name":"Hanlin Zhang","orcid":"https://orcid.org/0000-0001-8869-6863"},"institutions":[{"id":"https://openalex.org/I108688024","display_name":"Qingdao University","ror":"https://ror.org/021cj6z65","country_code":"CN","type":"education","lineage":["https://openalex.org/I108688024"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanlin Zhang","raw_affiliation_strings":["Qingdao University, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0001-8869-6863","affiliations":[{"raw_affiliation_string":"Qingdao University, Qingdao, China","institution_ids":["https://openalex.org/I108688024"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010106841","display_name":"Peng Zhao","orcid":"https://orcid.org/0000-0001-7033-9315"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Zhao","raw_affiliation_strings":["Xi&#x0027;an Jiaotong University, Xi&#x0027;an, China"],"raw_orcid":"https://orcid.org/0000-0001-7033-9315","affiliations":[{"raw_affiliation_string":"Xi&#x0027;an Jiaotong University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02996105,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":"5","first_page":"3665","last_page":"3676"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7858999967575073,"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":0.7858999967575073,"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":0.7631057500839233},{"id":"https://openalex.org/keywords/competition","display_name":"Competition (biology)","score":0.7106455564498901},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6665921211242676},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.45188769698143005},{"id":"https://openalex.org/keywords/complete-information","display_name":"Complete information","score":0.4155201315879822},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35899561643600464},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.20914915204048157},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.14729636907577515},{"id":"https://openalex.org/keywords/ecology","display_name":"Ecology","score":0.1270972490310669},{"id":"https://openalex.org/keywords/microeconomics","display_name":"Microeconomics","score":0.1270674467086792},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.107113778591156},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.10024169087409973}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7631057500839233},{"id":"https://openalex.org/C91306197","wikidata":"https://www.wikidata.org/wiki/Q45767","display_name":"Competition (biology)","level":2,"score":0.7106455564498901},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6665921211242676},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45188769698143005},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.4155201315879822},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35899561643600464},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.20914915204048157},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.14729636907577515},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.1270972490310669},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.1270674467086792},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.107113778591156},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.10024169087409973}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tetci.2025.3555250","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetci.2025.3555250","pdf_url":null,"source":{"id":"https://openalex.org/S4210210251","display_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","issn_l":"2471-285X","issn":["2471-285X"],"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 Emerging Topics in Computational Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1788318512","https://openalex.org/W2051203581","https://openalex.org/W2114500662","https://openalex.org/W2123108597","https://openalex.org/W2145339207","https://openalex.org/W2172968643","https://openalex.org/W2963523627","https://openalex.org/W2970593348","https://openalex.org/W2998557583","https://openalex.org/W3006086787","https://openalex.org/W3017262417","https://openalex.org/W3041349757","https://openalex.org/W3046385005","https://openalex.org/W3092156990","https://openalex.org/W3133092968","https://openalex.org/W3181648466","https://openalex.org/W4229041186","https://openalex.org/W4380358585","https://openalex.org/W4385488604"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"The":[0,221],"sparse":[1,139],"reward":[2,120,140],"problem":[3],"widely":[4],"exists":[5],"in":[6,19,55,71,82,100,123,133,238],"multi-agent":[7,101],"deep":[8,56,102],"reinforcement":[9,57,103],"learning,":[10,58],"preventing":[11],"agents":[12],"from":[13],"learning":[14,104],"optimal":[15],"actions":[16],"and":[17,34,95,163,186,235],"resulting":[18],"inefficient":[20,62],"interactions":[21],"with":[22,240],"the":[23,44,50,93,111,118,129,138,146,161,179,182,188,197,205],"environment.":[24],"Many":[25],"efforts":[26],"have":[27],"been":[28],"made":[29],"to":[30,61,90,109,127],"design":[31],"denser":[32],"rewards":[33,132],"promote":[35],"agent":[36],"exploration.":[37,201],"However,":[38],"existing":[39,183,241],"methods":[40],"only":[41],"focus":[42],"on":[43,211],"breadth":[45,94,162],"of":[46,52,97,113,131,165,181,190,193,199,207],"action":[47,53,63,79,98,114,134,167,191,200,232],"exploration,":[48,135],"neglecting":[49],"rationality":[51,96,164,189],"exploration":[54,64,80,115,168,192,233],"which":[59,159],"leads":[60],"for":[65,105,116,169],"agents.":[66,170],"To":[67],"address":[68],"this":[69,72],"issue,":[70],"paper,":[73],"we":[74,153,203],"propose":[75,154],"a":[76],"novel":[77],"curiosity-based":[78],"method":[81,126,176,210,227],"incomplete":[83,213],"information":[84,214],"competition":[85],"game":[86],"environments,":[87],"namely":[88,217],"IGC,":[89],"improve":[91],"both":[92,230],"exploitation":[99],"sparse-reward":[106],"environments.":[107],"Particularly,":[108],"enhance":[110],"capability":[112],"agents,":[117,194],"distance":[119],"is":[121],"designed":[122],"our":[124,174,208,225],"IGC":[125,175,209,226],"increase":[128,187],"density":[130],"thereby":[136,195],"mitigating":[137],"problem.":[141],"In":[142],"addition,":[143],"by":[144],"integrating":[145],"Intrinsic":[147],"Curiosity":[148],"Module":[149],"(ICM)":[150],"into":[151],"DQN,":[152],"an":[155,212],"enhanced":[156],"ICM-DQN":[157],"module,":[158],"enhances":[160],"subject":[166],"By":[171],"doing":[172],"this,":[173],"can":[177,228],"mitigate":[178],"randomness":[180],"curiosity":[184],"mechanism":[185],"enhancing":[196],"efficiency":[198,234],"Finally,":[202],"evaluate":[204],"effectiveness":[206],"card":[215,219],"game,":[216],"Uno":[218],"game.":[220],"results":[222],"demonstrate":[223],"that":[224],"achieve":[229],"better":[231],"greater":[236],"winning-rate":[237],"comparison":[239],"methods.":[242]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
