{"id":"https://openalex.org/W4404925298","doi":"https://doi.org/10.1145/3696271.3696296","title":"Entropy-Guided Exploration in AlphaZero: Enhancing MCTS with Information Gain for Strategic Decision Making","display_name":"Entropy-Guided Exploration in AlphaZero: Enhancing MCTS with Information Gain for Strategic Decision Making","publication_year":2024,"publication_date":"2024-08-02","ids":{"openalex":"https://openalex.org/W4404925298","doi":"https://doi.org/10.1145/3696271.3696296"},"language":"en","primary_location":{"id":"doi:10.1145/3696271.3696296","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3696271.3696296","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 7th International Conference on Machine Learning and Machine Intelligence (MLMI)","raw_type":"proceedings-article"},"type":"conference-paper","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":"Shuqin Li","orcid":"https://orcid.org/0000-0001-9909-5449"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuqin Li","raw_affiliation_strings":["School of Computer Science, Hangzhou Dianzi University Information Engineering College, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9909-5449","affiliations":[{"raw_affiliation_string":"School of Computer Science, Hangzhou Dianzi University Information Engineering College, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076787595","display_name":"Xueli Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueli Jia","raw_affiliation_strings":["School of Computer Science, Hangzhou Dianzi University Information Engineering College, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-8731-006X","affiliations":[{"raw_affiliation_string":"School of Computer Science, Hangzhou Dianzi University Information Engineering College, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yadong Zhou","orcid":"https://orcid.org/0009-0000-4639-9449"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yadong Zhou","raw_affiliation_strings":["School of Computer Science, Hangzhou Dianzi University Information Engineering College, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-4639-9449","affiliations":[{"raw_affiliation_string":"School of Computer Science, Hangzhou Dianzi University Information Engineering College, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015644606","display_name":"Dong Bin Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Xu","raw_affiliation_strings":["School of Computer Science, Hangzhou Dianzi University Information Engineering College, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-9887-643X","affiliations":[{"raw_affiliation_string":"School of Computer Science, Hangzhou Dianzi University Information Engineering College, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042528213","display_name":"H. M. Zhang","orcid":"https://orcid.org/0009-0002-0038-0771"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiping Zhang","raw_affiliation_strings":["School of Computer Science, Hangzhou Dianzi University Information Engineering College, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-0038-0771","affiliations":[{"raw_affiliation_string":"School of Computer Science, Hangzhou Dianzi University Information Engineering College, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046163744","display_name":"Miao Hu","orcid":"https://orcid.org/0000-0002-8843-4318"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Miao Hu","raw_affiliation_strings":["School of Communication Engineering, Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-8843-4318","affiliations":[{"raw_affiliation_string":"School of Communication Engineering, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I50760025"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"151","last_page":"156"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9955999851226807,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9955999851226807,"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":0.9955000281333923,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9846000075340271,"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/computer-science","display_name":"Computer science","score":0.6003400683403015},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5202102065086365},{"id":"https://openalex.org/keywords/information-gain","display_name":"Information gain","score":0.5082425475120544},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.3404809236526489},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31029993295669556}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6003400683403015},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5202102065086365},{"id":"https://openalex.org/C2983203078","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Information gain","level":2,"score":0.5082425475120544},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3404809236526489},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31029993295669556},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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:10.1145/3696271.3696296","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3696271.3696296","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 7th International Conference on Machine Learning and Machine Intelligence (MLMI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1543187661","https://openalex.org/W1872312298","https://openalex.org/W1995875735","https://openalex.org/W2020135152","https://openalex.org/W2112796928","https://openalex.org/W2113092063","https://openalex.org/W2126316555","https://openalex.org/W2145339207","https://openalex.org/W2167789032","https://openalex.org/W2417786368","https://openalex.org/W2750605955","https://openalex.org/W2766447205","https://openalex.org/W2907738974","https://openalex.org/W2946481965","https://openalex.org/W2989847975","https://openalex.org/W3118210634","https://openalex.org/W4285796263","https://openalex.org/W4387635629","https://openalex.org/W4389422760","https://openalex.org/W4390437612","https://openalex.org/W4393178239","https://openalex.org/W6636578284","https://openalex.org/W6637441126","https://openalex.org/W6687483927","https://openalex.org/W6712451147"],"related_works":["https://openalex.org/W1998236653","https://openalex.org/W1972259667","https://openalex.org/W2388707026","https://openalex.org/W2900925991","https://openalex.org/W2092738042","https://openalex.org/W4308273529","https://openalex.org/W2347586617","https://openalex.org/W2071645312","https://openalex.org/W1795191888","https://openalex.org/W2120402301"],"abstract_inverted_index":{"AlphaZero":[0,21],"has":[1],"revolutionized":[2],"AI":[3,110],"game-playing,":[4],"yet":[5],"it":[6,41],"may":[7],"overlook":[8],"actions":[9],"crucial":[10],"for":[11],"long-term":[12],"strategy.":[13],"This":[14],"paper":[15],"introduces":[16],"Entropy-Guided":[17],"MCTS":[18,43],"(EG-MCTS),":[19],"enhancing":[20],"by":[22],"incorporating":[23],"information":[24,32,64],"theory":[25],"into":[26,42],"action":[27],"selection.":[28],"We":[29],"propose":[30],"an":[31],"gain":[33,65],"metric":[34],"based":[35],"on":[36],"game":[37,86],"state":[38],"entropy,":[39],"integrating":[40],"to":[44,91],"balance":[45],"immediate":[46],"rewards":[47],"with":[48,66],"informational":[49],"value.":[50],"Our":[51],"contributions":[52],"include":[53],"developing":[54],"this":[55],"metric,":[56],"modifying":[57],"neural":[58],"network":[59],"training,":[60],"and":[61,89],"systematically":[62],"balancing":[63],"existing":[67],"criteria.":[68],"Comprehensive":[69],"evaluations":[70],"across":[71],"various":[72],"games":[73],"demonstrate":[74],"EG-MCTS's":[75],"improved":[76],"performance":[77],"in":[78,85,99],"complex":[79],"strategic":[80],"scenarios,":[81],"showing":[82],"enhanced":[83],"efficiency":[84],"tree":[87],"navigation":[88],"adaptation":[90],"unfamiliar":[92],"situations.":[93],"These":[94],"findings":[95],"suggest":[96],"broader":[97],"applications":[98],"sequential":[100],"decision-making":[101],"under":[102],"uncertainty,":[103],"advancing":[104],"the":[105],"development":[106],"of":[107],"more":[108],"adaptable":[109],"systems.":[111]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
