{"id":"https://openalex.org/W4414359245","doi":"https://doi.org/10.24963/ijcai.2025/1170","title":"Survey on Strategic Mining in Blockchain: A Reinforcement Learning Approach","display_name":"Survey on Strategic Mining in Blockchain: A Reinforcement Learning Approach","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359245","doi":"https://doi.org/10.24963/ijcai.2025/1170"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/1170","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/1170","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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":"https://openalex.org/A5102028046","display_name":"Jichen Li","orcid":"https://orcid.org/0000-0002-8711-5040"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jichen Li","raw_affiliation_strings":["Peking University","Zhongguancun Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Zhongguancun Laboratory","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101638016","display_name":"Lijia Xie","orcid":"https://orcid.org/0000-0003-0027-9032"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lijia Xie","raw_affiliation_strings":["Zhongguancun Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhongguancun Laboratory","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hanting Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanting Huang","raw_affiliation_strings":["Beihang University","Zhongguancun Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Zhongguancun Laboratory","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100335177","display_name":"Bo Zhou","orcid":"https://orcid.org/0000-0001-6336-4651"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Zhou","raw_affiliation_strings":["Zhongguancun Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhongguancun Laboratory","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006119430","display_name":"Bin Song","orcid":"https://orcid.org/0000-0001-8929-2756"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Binfeng Song","raw_affiliation_strings":["Beihang University","Zhongguancun Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Zhongguancun Laboratory","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076490305","display_name":"Wanying Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanying Zeng","raw_affiliation_strings":["Beihang University","Zhongguancun Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Zhongguancun Laboratory","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100638710","display_name":"Xiaotie Deng","orcid":"https://orcid.org/0000-0002-5282-6467"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaotie Deng","raw_affiliation_strings":["Peking University","Zhongguancun Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Zhongguancun Laboratory","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032417256","display_name":"Xiao Zhang","orcid":"https://orcid.org/0000-0003-4927-5016"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Zhang","raw_affiliation_strings":["Beihang University","Zhongguancun Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Zhongguancun Laboratory","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"10537","last_page":"10545"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10270","display_name":"Blockchain Technology Applications and Security","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10270","display_name":"Blockchain Technology Applications and Security","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8622999787330627},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6557999849319458},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6506999731063843},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5127999782562256},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.48350000381469727},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4207000136375427},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.29789999127388}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8622999787330627},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7365999817848206},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6557999849319458},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6506999731063843},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5127999782562256},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.48350000381469727},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4207000136375427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39559999108314514},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.33390000462532043},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3163999915122986},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.29789999127388},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2964000105857849},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C2778464652","wikidata":"https://www.wikidata.org/wiki/Q309849","display_name":"Open research","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C48243021","wikidata":"https://www.wikidata.org/wiki/Q932522","display_name":"Strategic planning","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C199776023","wikidata":"https://www.wikidata.org/wiki/Q202875","display_name":"Negotiation","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.25429999828338623},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/1170","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/1170","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Strategic":[0],"mining":[1,61],"attacks,":[2],"such":[3,105,127],"as":[4,106,128],"selfish":[5,147],"mining,":[6,148],"exploit":[7],"blockchain":[8],"consensus":[9,121],"protocols":[10,122],"by":[11,70],"deviating":[12],"from":[13],"honest":[14],"behavior":[15],"to":[16,65,142],"maximize":[17],"rewards.":[18],"Markov":[19],"Decision":[20],"Process":[21],"(MDP)":[22],"analysis":[23],"faces":[24],"scalability":[25],"challenges":[26,145],"in":[27,48,59,101,164],"modern":[28],"digital":[29],"economics,":[30],"including":[31,149],"blockchain.":[32],"To":[33],"address":[34,143],"these":[35],"limitations,":[36,77],"reinforcement":[37,140],"learning":[38,141],"(RL)":[39],"provides":[40],"a":[41,159],"scalable":[42],"alternative,":[43],"enabling":[44],"adaptive":[45],"strategy":[46],"optimization":[47],"complex":[49],"dynamic":[50],"environments.":[51],"In":[52],"this":[53,92],"survey,":[54],"we":[55,94,119],"examine":[56],"RL\u2019s":[57],"role":[58],"strategic":[60,160],"analysis,":[62,93,156],"comparing":[63],"it":[64],"MDP-based":[66],"approaches.":[67],"We":[68],"begin":[69],"reviewing":[71],"foundational":[72],"MDP":[73],"models":[74],"and":[75,98,123,131,154,167],"their":[76,99],"before":[78],"exploring":[79],"RL":[80,96],"frameworks":[81],"that":[82],"can":[83],"learn":[84],"near-optimal":[85],"strategies":[86],"across":[87],"various":[88],"protocols.":[89],"Building":[90],"on":[91],"compare":[95],"techniques":[97],"effectiveness":[100],"deriving":[102],"security":[103,155],"thresholds,":[104],"the":[107,116,137,144],"minimum":[108],"attacker":[109],"power":[110],"required":[111],"for":[112,162],"profitable":[113],"attacks.":[114],"Expanding":[115],"discussion":[117],"further,":[118],"classify":[120],"propose":[124],"open":[125],"challenges,":[126],"multi-agent":[129],"dynamics":[130],"real-world":[132],"validation.":[133],"This":[134],"survey":[135],"highlights":[136],"potential":[138],"of":[139,146],"protocol":[150],"design,":[151],"threat":[152],"detection,":[153],"while":[157],"offering":[158],"roadmap":[161],"researchers":[163],"decentralized":[165],"systems":[166],"AI-driven":[168],"analytics.":[169]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}