{"id":"https://openalex.org/W7125916223","doi":"https://doi.org/10.1109/smc58881.2025.11343590","title":"Balancing Exploration and Exploitation in Maximum Diffusion Reinforcement Learning Using Evolutionary Computation Algorithm","display_name":"Balancing Exploration and Exploitation in Maximum Diffusion Reinforcement Learning Using Evolutionary Computation Algorithm","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125916223","doi":"https://doi.org/10.1109/smc58881.2025.11343590"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11343590","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343590","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5123199620","display_name":"Ying Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ying Zhao","raw_affiliation_strings":["University of Aizu,Graduate School of Computer Science and Engineering,Aizuwakamatsu,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Aizu,Graduate School of Computer Science and Engineering,Aizuwakamatsu,Japan","institution_ids":["https://openalex.org/I141591182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124086670","display_name":"Yan Pei","orcid":null},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yan Pei","raw_affiliation_strings":["University of Aizu,Computer Science Division,Aizuwakamatsu,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Aizu,Computer Science Division,Aizuwakamatsu,Japan","institution_ids":["https://openalex.org/I141591182"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I141591182"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.65446191,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5546","last_page":"5551"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9307000041007996,"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":0.9307000041007996,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.041099999099969864,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.0026000000070780516,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7714999914169312},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5885000228881836},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5443999767303467},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5250999927520752},{"id":"https://openalex.org/keywords/evolutionary-algorithm","display_name":"Evolutionary algorithm","score":0.47780001163482666},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.45579999685287476},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.420199990272522},{"id":"https://openalex.org/keywords/evolutionary-computation","display_name":"Evolutionary computation","score":0.4187000095844269}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7714999914169312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6220999956130981},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5885000228881836},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5443999767303467},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5250999927520752},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.47780001163482666},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.45579999685287476},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.45339998602867126},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.420199990272522},{"id":"https://openalex.org/C105902424","wikidata":"https://www.wikidata.org/wiki/Q1197129","display_name":"Evolutionary computation","level":2,"score":0.4187000095844269},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3813999891281128},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.34790000319480896},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3382999897003174},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.3190999925136566},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31540000438690186},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C168031717","wikidata":"https://www.wikidata.org/wiki/Q1530280","display_name":"Balance (ability)","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C2987595161","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Optimization algorithm","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2556000053882599},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11343590","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343590","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.44563403725624084}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2032558547","https://openalex.org/W2141559645","https://openalex.org/W2158782408","https://openalex.org/W2738778707","https://openalex.org/W2907537824","https://openalex.org/W2951278471","https://openalex.org/W3038822267","https://openalex.org/W4396583645","https://openalex.org/W4404125296"],"related_works":[],"abstract_inverted_index":{"Balancing":[0],"exploration":[1,81],"and":[2,82,97,118],"exploitation":[3],"is":[4,20,35,59],"a":[5,23,43,77],"fundamental":[6],"challenge":[7],"in":[8,93,123],"reinforcement":[9],"learning.":[10],"In":[11],"Maximum":[12],"Diffusion":[13],"Reinforcement":[14],"Learning":[15],"(MaxDiff":[16],"RL),":[17],"this":[18,39],"balance":[19,79],"regulated":[21],"by":[22],"temperature":[24,49,74,113],"parameter":[25,50],"that":[26,45,102],"controls":[27],"exploration,":[28],"but":[29],"optimizing":[30],"it":[31],"across":[32],"different":[33,65],"tasks":[34,92,124],"challenging.":[36],"To":[37],"tackle":[38],"issue,":[40],"we":[41],"propose":[42],"method":[44,87,104],"dynamically":[46],"adjusts":[47],"the":[48,73],"via":[51],"evolutionary":[52],"algorithms":[53,107],"during":[54],"training.":[55],"The":[56],"training":[57],"process":[58],"divided":[60],"into":[61],"multiple":[62],"stages,":[63],"where":[64],"optimization":[66],"strategies":[67],"are":[68],"applied":[69],"to":[70],"adaptively":[71],"evolve":[72],"parameter,":[75],"ensuring":[76],"proper":[78],"between":[80],"exploitation.":[83],"We":[84],"evaluate":[85],"our":[86,103],"on":[88],"two":[89],"continuous":[90],"control":[91],"robotics,":[94],"i.e.,":[95],"Swimmer":[96],"HalfCheetah.":[98],"Experimental":[99],"results":[100],"demonstrate":[101],"outperforms":[105],"baseline":[106],"with":[108],"randomly":[109],"initialized":[110],"or":[111],"default":[112],"parameters,":[114],"achieving":[115],"faster":[116],"convergence":[117],"higher":[119],"cumulative":[120],"rewards,":[121],"particularly":[122],"demanding":[125],"greater":[126],"exploration.":[127]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-01-29T00:00:00"}