{"id":"https://openalex.org/W4390357424","doi":"https://doi.org/10.1109/access.2023.3347803","title":"Boosting Policy Learning in Reinforcement Learning via Adaptive Intrinsic Reward Regulation","display_name":"Boosting Policy Learning in Reinforcement Learning via Adaptive Intrinsic Reward Regulation","publication_year":2023,"publication_date":"2023-12-28","ids":{"openalex":"https://openalex.org/W4390357424","doi":"https://doi.org/10.1109/access.2023.3347803"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3347803","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/access.2023.3347803","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10375485.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10375485.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086649532","display_name":"Qian Zhao","orcid":"https://orcid.org/0000-0002-3758-237X"},"institutions":[{"id":"https://openalex.org/I4210093674","display_name":"Zhoukou Normal University","ror":"https://ror.org/00jjkh886","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210093674"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Zhao","raw_affiliation_strings":["School of Physics and Telecommunication Engineering, Zhoukou Normal University, Zhoukou, China"],"raw_orcid":"https://orcid.org/0000-0002-3758-237X","affiliations":[{"raw_affiliation_string":"School of Physics and Telecommunication Engineering, Zhoukou Normal University, Zhoukou, China","institution_ids":["https://openalex.org/I4210093674"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071258855","display_name":"Jinhui Han","orcid":"https://orcid.org/0000-0002-2149-5589"},"institutions":[{"id":"https://openalex.org/I4210093674","display_name":"Zhoukou Normal University","ror":"https://ror.org/00jjkh886","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210093674"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinhui Han","raw_affiliation_strings":["School of Physics and Telecommunication Engineering, Zhoukou Normal University, Zhoukou, China"],"raw_orcid":"https://orcid.org/0000-0002-2149-5589","affiliations":[{"raw_affiliation_string":"School of Physics and Telecommunication Engineering, Zhoukou Normal University, Zhoukou, China","institution_ids":["https://openalex.org/I4210093674"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064117374","display_name":"Mao Xu","orcid":"https://orcid.org/0000-0003-4549-1221"},"institutions":[{"id":"https://openalex.org/I4210093674","display_name":"Zhoukou Normal University","ror":"https://ror.org/00jjkh886","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210093674"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mao Xu","raw_affiliation_strings":["School of Physics and Telecommunication Engineering, Zhoukou Normal University, Zhoukou, China"],"raw_orcid":"https://orcid.org/0000-0003-4549-1221","affiliations":[{"raw_affiliation_string":"School of Physics and Telecommunication Engineering, Zhoukou Normal University, Zhoukou, China","institution_ids":["https://openalex.org/I4210093674"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.4895,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72579922,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":"12","issue":null,"first_page":"2224","last_page":"2235"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9986000061035156,"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"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.998199999332428,"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":0.7559899091720581},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7042431831359863},{"id":"https://openalex.org/keywords/intrinsic-motivation","display_name":"Intrinsic motivation","score":0.6506279110908508},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.491361528635025},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.4818197786808014},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46938130259513855},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4604312777519226},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0988798439502716}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7559899091720581},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7042431831359863},{"id":"https://openalex.org/C2985564149","wikidata":"https://www.wikidata.org/wiki/Q644302","display_name":"Intrinsic motivation","level":2,"score":0.6506279110908508},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.491361528635025},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.4818197786808014},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46938130259513855},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4604312777519226},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0988798439502716},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2023.3347803","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/access.2023.3347803","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10375485.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:99145b4ab67c48528d3d799a0e31dac2","is_oa":true,"landing_page_url":"https://doaj.org/article/99145b4ab67c48528d3d799a0e31dac2","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 2224-2235 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3347803","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/access.2023.3347803","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10375485.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1087481077","display_name":null,"funder_award_id":"U1813202","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G307135022","display_name":null,"funder_award_id":"222102210077","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4531927070","display_name":null,"funder_award_id":"U1813202","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4760286927","display_name":null,"funder_award_id":"2020YFB1313600","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5666800812","display_name":null,"funder_award_id":"222102210077","funder_id":"https://openalex.org/F4320327051","funder_display_name":"Science and Technology Department of Henan Province"},{"id":"https://openalex.org/G6506257578","display_name":null,"funder_award_id":"62003381","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6865181076","display_name":null,"funder_award_id":"212102210525","funder_id":"https://openalex.org/F4320327051","funder_display_name":"Science and Technology Department of Henan Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327051","display_name":"Science and Technology Department of Henan Province","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390357424.pdf","grobid_xml":"https://content.openalex.org/works/W4390357424.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W21891419","https://openalex.org/W779494576","https://openalex.org/W1625390266","https://openalex.org/W1863227302","https://openalex.org/W1988526405","https://openalex.org/W2077148472","https://openalex.org/W2101524054","https://openalex.org/W2108114251","https://openalex.org/W2236244207","https://openalex.org/W2914261249","https://openalex.org/W2963523627","https://openalex.org/W2963871073","https://openalex.org/W2974778612","https://openalex.org/W3100329718","https://openalex.org/W3111378514","https://openalex.org/W3171210634","https://openalex.org/W4214717370","https://openalex.org/W6622487243","https://openalex.org/W6628764021","https://openalex.org/W6676576766","https://openalex.org/W6679661297","https://openalex.org/W6692846177","https://openalex.org/W6716474083","https://openalex.org/W6717230150","https://openalex.org/W6718092244","https://openalex.org/W6735033012","https://openalex.org/W6735939104","https://openalex.org/W6737937804","https://openalex.org/W6739193204","https://openalex.org/W6754891083","https://openalex.org/W6756303580","https://openalex.org/W6758978475","https://openalex.org/W6762863188","https://openalex.org/W6771807793","https://openalex.org/W6771968188","https://openalex.org/W6779637449","https://openalex.org/W6780486084","https://openalex.org/W6788860121","https://openalex.org/W6789598788","https://openalex.org/W6797415283","https://openalex.org/W6800937065","https://openalex.org/W6803654719","https://openalex.org/W6846255677"],"related_works":["https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W1549363203","https://openalex.org/W2147697413","https://openalex.org/W2154063878","https://openalex.org/W4231274751","https://openalex.org/W2556012038","https://openalex.org/W1489772951","https://openalex.org/W3082059448","https://openalex.org/W4313640622"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,9,79,213],"employs":[2],"heuristic":[3],"intrinsic":[4,39,47,70,92,109,133,155,177,201],"rewards":[5,34,40,48,93],"to":[6,28,75,90,149,167,223],"facilitate":[7],"effective":[8],"and":[10,55,81,190,215],"exploration":[11,54],"of":[12,68,102,106,115,132,154,219],"the":[13,69,100,104,130,140,151,160,175,181,208,217],"environment":[14],"by":[15,61,94,172],"intelligent":[16],"agents.":[17],"Particularly":[18],"in":[19,78,121,163,174,187],"environments":[20,193],"with":[21,99,194,199],"sparse":[22,195],"rewards,":[23,134,196],"it\u2019s":[24],"challenging":[25],"for":[26],"agents":[27],"reach":[29],"goals":[30],"or":[31],"obtain":[32],"extrinsic":[33],"through":[35],"random":[36],"exploration.":[37],"Appropriate":[38],"can":[41,73,118],"significantly":[42],"boost":[43],"learning.":[44],"However,":[45],"using":[46],"requires":[49],"a":[50,62,87,126,224],"careful":[51],"balance":[52],"between":[53],"exploitation,":[56],"which":[57,135],"is":[58],"typically":[59],"adjusted":[60],"coefficient.":[63],"In":[64],"addition,":[65],"different":[66],"settings":[67],"reward":[71,110,156,202],"coefficient":[72,127],"lead":[74],"significant":[76],"differences":[77],"efficiency":[80,153,214],"performance.":[82],"Hence,":[83],"this":[84,116],"paper":[85],"presents":[86],"novel":[88],"approach":[89],"regulate":[91],"adaptively":[95],"tuning":[96],"their":[97],"coefficients,":[98],"aim":[101],"enhancing":[103],"performance":[105,218],"some":[107,220],"existing":[108,221],"techniques.":[111],"The":[112,204],"primary":[113],"contributions":[114],"study":[117],"be":[119],"summarized":[120],"three":[122],"aspects:":[123],"1)":[124],"Designing":[125],"that":[128,207],"adjusts":[129],"magnitude":[131],"dynamically":[136],"adapts":[137],"based":[138],"on":[139],"return":[141],"curve.":[142],"2)":[143],"Developing":[144],"an":[145],"episode-wise":[146],"adjustment":[147],"strategy":[148],"improve":[150],"sample":[152],"methods.":[157],"3)":[158],"Modifying":[159],"advantage":[161],"function":[162],"gradient":[164],"policy":[165],"methods":[166],"mitigate":[168],"training":[169],"instability":[170],"caused":[171],"changes":[173],"regulated":[176],"rewards.":[178],"To":[179],"evaluate":[180],"proposed":[182,209],"method,":[183],"we":[184],"conducted":[185],"experiments":[186],"both":[188],"2D":[189],"3D":[191],"maze":[192],"combining":[197],"it":[198],"several":[200],"approaches.":[203],"results":[205],"demonstrate":[206],"method":[210],"effectively":[211],"enhances":[212],"improves":[216],"approaches":[222],"certain":[225],"extent.":[226]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}