{"id":"https://openalex.org/W2553188523","doi":"https://doi.org/10.1609/aaai.v30i1.10285","title":"Efficient Average Reward Reinforcement Learning Using Constant Shifting Values","display_name":"Efficient Average Reward Reinforcement Learning Using Constant Shifting Values","publication_year":2016,"publication_date":"2016-03-02","ids":{"openalex":"https://openalex.org/W2553188523","doi":"https://doi.org/10.1609/aaai.v30i1.10285","mag":"2553188523"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v30i1.10285","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v30i1.10285","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v30i1.10285","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100764370","display_name":"Shangdong Yang","orcid":"https://orcid.org/0000-0001-5379-9539"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shangdong Yang","raw_affiliation_strings":["Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074250521","display_name":"Yang Gao","orcid":"https://orcid.org/0000-0002-2488-1813"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Gao","raw_affiliation_strings":["Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017743551","display_name":"Bo An","orcid":"https://orcid.org/0000-0002-7064-7438"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bo An","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101533496","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0003-2129-2148"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025828195","display_name":"Xingguo Chen","orcid":"https://orcid.org/0000-0002-0221-733X"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingguo Chen","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1331,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.90601781,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"30","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9891999959945679,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9753000140190125,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.8281155824661255},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6533308029174805},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.6113316416740417},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5776286721229553},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5300756692886353},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.4158298373222351},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39304235577583313},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38060876727104187},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3062021732330322}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8281155824661255},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6533308029174805},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.6113316416740417},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5776286721229553},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5300756692886353},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.4158298373222351},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39304235577583313},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38060876727104187},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3062021732330322},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v30i1.10285","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v30i1.10285","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/10285","is_oa":true,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/10285","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/10285/10144","source":{"id":"https://openalex.org/S7407064318","display_name":"AAAI Publications","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v30i1.10285","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v30i1.10285","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1649257048","display_name":null,"funder_award_id":"61503178","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3836653666","display_name":null,"funder_award_id":"61321491","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G5394304682","display_name":"\u9762\u5411\u5927\u6570\u636e\u7684\u77e5\u8bc6\u8868\u793a\u3001\u63a8\u7406\u3001\u5728\u7ebf\u5b66\u4e60\u7406\u8bba\u53ca\u5e94\u7528\u7814\u7a76","funder_award_id":"61432008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5616286496","display_name":null,"funder_award_id":"61175042","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6667581590","display_name":null,"funder_award_id":"61321491","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6710017015","display_name":null,"funder_award_id":"BK20150587","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G8143510668","display_name":null,"funder_award_id":"61403208","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321605","display_name":"Government of Jiangsu Province","ror":"https://ror.org/004svx814"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W359568995","https://openalex.org/W1549353711","https://openalex.org/W1588508200","https://openalex.org/W1605318140","https://openalex.org/W1774379669","https://openalex.org/W1850488217","https://openalex.org/W1991138660","https://openalex.org/W1998645260","https://openalex.org/W2071815241","https://openalex.org/W2075268401","https://openalex.org/W2075754841","https://openalex.org/W2097931172","https://openalex.org/W2101242010","https://openalex.org/W2101915445","https://openalex.org/W2107726111","https://openalex.org/W2111625864","https://openalex.org/W2111764152","https://openalex.org/W2115330428","https://openalex.org/W2121863487","https://openalex.org/W2143496582","https://openalex.org/W2146302034","https://openalex.org/W2154204727","https://openalex.org/W2165905123","https://openalex.org/W2951592473","https://openalex.org/W3020125231","https://openalex.org/W3136998346","https://openalex.org/W3139474403","https://openalex.org/W4214717370","https://openalex.org/W4229915002","https://openalex.org/W4300983094","https://openalex.org/W6638149894","https://openalex.org/W6649887360","https://openalex.org/W6676007687","https://openalex.org/W6677415531"],"related_works":["https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W2154399718","https://openalex.org/W4321463377","https://openalex.org/W2768629321","https://openalex.org/W2130711276","https://openalex.org/W4308828368","https://openalex.org/W1528400370","https://openalex.org/W3038962357","https://openalex.org/W2189613824"],"abstract_inverted_index":{"There":[0],"are":[1,30],"two":[2],"classes":[3],"of":[4,47,61,95,103],"average":[5],"reward":[6],"reinforcement":[7],"learning":[8,75],"(RL)":[9],"algorithms:":[10],"model-based":[11],"ones":[12,20],"that":[13,21,138],"explicitly":[14],"maintain":[15],"MDP":[16],"models":[17],"and":[18,132],"model-free":[19,28,54],"do":[22],"not":[23],"learn":[24],"such":[25,99],"models.":[26],"Though":[27],"algorithms":[29,141],"known":[31],"to":[32,40,44,91,119,123],"be":[33],"more":[34],"efficient,":[35],"they":[36],"often":[37],"cannot":[38],"converge":[39],"optimal":[41],"policies":[42],"due":[43],"the":[45,74,77,81,84,93,104,133,139,144],"perturbation":[46],"parameters.":[48],"In":[49],"this":[50],"paper,":[51],"a":[52],"novel":[53],"algorithm":[55,78,106],"is":[56,89,107,117],"proposed,":[57],"which":[58],"makes":[59],"use":[60],"constant":[62],"shifting":[63],"values":[64],"(CSVs)":[65],"estimated":[66],"from":[67,83],"prior":[68],"knowledge.":[69],"To":[70],"encourage":[71],"exploration":[72],"during":[73],"process,":[76],"constantly":[79],"subtracts":[80],"CSV":[82],"rewards.":[85],"A":[86],"terminating":[87],"condition":[88],"proposed":[90,105,140],"handle":[92,124],"unboundedness":[94],"Q-values":[96],"caused":[97],"by":[98],"substraction.":[100],"The":[101],"convergence":[102],"proved":[108],"under":[109],"very":[110],"mild":[111],"assumptions.":[112],"Furthermore,":[113],"linear":[114],"function":[115],"approximation":[116],"investigated":[118],"generalize":[120],"our":[121],"method":[122],"large-scale":[125],"tasks.":[126],"Extensive":[127],"experiments":[128],"on":[129],"representative":[130],"MDPs":[131],"popular":[134],"game":[135],"Tetris":[136],"show":[137],"significantly":[142],"outperform":[143],"state-of-the-art":[145],"ones.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2}],"updated_date":"2026-09-02T07:38:04.252551","created_date":"2025-10-10T00:00:00"}