{"id":"https://openalex.org/W3192314531","doi":"https://doi.org/10.24963/ijcai.2021/385","title":"Average-Reward Reinforcement Learning with Trust Region Methods","display_name":"Average-Reward Reinforcement Learning with Trust Region Methods","publication_year":2021,"publication_date":"2021-08-01","ids":{"openalex":"https://openalex.org/W3192314531","doi":"https://doi.org/10.24963/ijcai.2021/385","mag":"3192314531"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2021/385","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/385","pdf_url":"https://www.ijcai.org/proceedings/2021/0385.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2021/0385.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027912723","display_name":"Xiaoteng Ma","orcid":"https://orcid.org/0000-0002-7250-6268"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoteng Ma","raw_affiliation_strings":["Department of Automation, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004495956","display_name":"Xiaohang Tang","orcid":"https://orcid.org/0000-0002-2691-9280"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xiaohang Tang","raw_affiliation_strings":["Department of Statistical Science, University College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistical Science, University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100646502","display_name":"Li Xia","orcid":"https://orcid.org/0000-0002-3193-7336"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Xia","raw_affiliation_strings":["Business School, Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Business School, Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101912623","display_name":"Jun Yang","orcid":"https://orcid.org/0000-0002-9386-5825"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yang","raw_affiliation_strings":["Department of Automation, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014109600","display_name":"Qianchuan Zhao","orcid":"https://orcid.org/0000-0002-7952-5621"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianchuan Zhao","raw_affiliation_strings":["Department of Automation, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9795,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.80759451,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2797","last_page":"2803"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.989300012588501,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T10270","display_name":"Blockchain Technology Applications and Security","score":0.9879999756813049,"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":0.8811157941818237},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6176563501358032},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6056985855102539},{"id":"https://openalex.org/keywords/trust-region","display_name":"Trust region","score":0.5961103439331055},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5712714791297913},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5685777068138123},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5520359873771667},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4204046130180359},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.41372743248939514},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35956376791000366},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33922284841537476},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24726110696792603}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8811157941818237},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6176563501358032},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6056985855102539},{"id":"https://openalex.org/C89109886","wikidata":"https://www.wikidata.org/wiki/Q1535924","display_name":"Trust region","level":3,"score":0.5961103439331055},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5712714791297913},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5685777068138123},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5520359873771667},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4204046130180359},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.41372743248939514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35956376791000366},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33922284841537476},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24726110696792603},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C178635117","wikidata":"https://www.wikidata.org/wiki/Q747499","display_name":"RADIUS","level":2,"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/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2021/385","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/385","pdf_url":"https://www.ijcai.org/proceedings/2021/0385.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2021/385","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/385","pdf_url":"https://www.ijcai.org/proceedings/2021/0385.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3192314531.pdf","grobid_xml":"https://content.openalex.org/works/W3192314531.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1191599655","https://openalex.org/W1549353711","https://openalex.org/W1575592356","https://openalex.org/W1606011487","https://openalex.org/W1771410628","https://openalex.org/W1941445455","https://openalex.org/W2098432798","https://openalex.org/W2153874061","https://openalex.org/W2155027007","https://openalex.org/W2156737235","https://openalex.org/W2158782408","https://openalex.org/W2257979135","https://openalex.org/W2321292752","https://openalex.org/W2342662072","https://openalex.org/W2553188523","https://openalex.org/W2611866857","https://openalex.org/W2736601468","https://openalex.org/W2749928749","https://openalex.org/W2982316857","https://openalex.org/W2999044305","https://openalex.org/W3035700320","https://openalex.org/W3092703335","https://openalex.org/W4229915002","https://openalex.org/W4287725923","https://openalex.org/W4288118072","https://openalex.org/W4293545785","https://openalex.org/W4298023569","https://openalex.org/W4394666657"],"related_works":["https://openalex.org/W2080108722","https://openalex.org/W2752681920","https://openalex.org/W1997473290","https://openalex.org/W2353911672","https://openalex.org/W2393042414","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2058731384","https://openalex.org/W2920061524","https://openalex.org/W4385488867"],"abstract_inverted_index":{"Most":[0],"of":[1,20,123,147,178],"reinforcement":[2,55,148],"learning":[3,56,149],"algorithms":[4],"optimize":[5],"the":[6,14,18,23,54,59,77,85,91,109,121,129,134,139,145,151,159,171,176],"discounted":[7,24,72,152,172],"criterion":[8,25,141],"which":[9,107,174],"is":[10,26,88,128],"beneficial":[11],"to":[12,132],"accelerate":[13],"convergence":[15],"and":[16,43,73,142],"reduce":[17],"variance":[19],"estimates.":[21],"Although":[22],"appropriate":[27],"for":[28],"certain":[29],"tasks":[30],"such":[31],"as":[32],"financial":[33],"related":[34],"problems,":[35],"many":[36],"engineering":[37],"problems":[38],"treat":[39],"future":[40],"rewards":[41],"equally":[42],"prefer":[44],"a":[45,66,80,99,113],"long-run":[46,60],"average":[47,61,74,78,140],"criterion.":[48,62,153],"In":[49,164],"this":[50],"paper,":[51],"we":[52,64,97],"study":[53,133],"problem":[57],"with":[58,71,90,112,138],"Firstly,":[63],"develop":[65],"unified":[67],"trust":[68,86,135],"region":[69,87,136],"theory":[70],"criteria.":[75],"With":[76],"criterion,":[79],"novel":[81,114],"performance":[82],"bound":[83],"within":[84],"derived":[89],"Perturbation":[92],"Analysis":[93],"(PA)":[94],"theory.":[95],"Secondly,":[96],"propose":[98],"practical":[100],"algorithm":[101],"named":[102,116],"Average":[103,117],"Policy":[104],"Optimization":[105],"(APO),":[106],"improves":[108],"value":[110],"estimation":[111],"technique":[115],"Value":[118],"Constraint.":[119],"To":[120],"best":[122],"our":[124,126,179],"knowledge,":[125],"work":[127],"first":[130],"one":[131],"approach":[137],"it":[143],"complements":[144],"framework":[146],"beyond":[150],"Finally,":[154],"experiments":[155],"are":[156],"conducted":[157],"in":[158],"continuous":[160],"control":[161],"environment":[162],"MuJoCo.":[163],"most":[165],"tasks,":[166],"APO":[167],"performs":[168],"better":[169],"than":[170],"PPO,":[173],"demonstrates":[175],"effectiveness":[177],"approach.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}