{"id":"https://openalex.org/W4296512932","doi":"https://doi.org/10.1109/cog51982.2022.9893651","title":"Reinforcement Learning using Reward Expectations in Scenarios with Aleatoric Uncertainties","display_name":"Reinforcement Learning using Reward Expectations in Scenarios with Aleatoric Uncertainties","publication_year":2022,"publication_date":"2022-08-21","ids":{"openalex":"https://openalex.org/W4296512932","doi":"https://doi.org/10.1109/cog51982.2022.9893651"},"language":"en","primary_location":{"id":"doi:10.1109/cog51982.2022.9893651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog51982.2022.9893651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"},"type":"article","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/A5100757319","display_name":"Yubin Wang","orcid":"https://orcid.org/0000-0003-1640-4504"},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yubin Wang","raw_affiliation_strings":["PLA SSF Information Engineering University,Zhengzhou,China","PLA SSF Information Engineering University, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"PLA SSF Information Engineering University,Zhengzhou,China","institution_ids":["https://openalex.org/I169689159"]},{"raw_affiliation_string":"PLA SSF Information Engineering University, Zhengzhou, China","institution_ids":["https://openalex.org/I169689159"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024097973","display_name":"Yi-Feng Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifeng Sun","raw_affiliation_strings":["PLA SSF Information Engineering University,Zhengzhou,China","PLA SSF Information Engineering University, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"PLA SSF Information Engineering University,Zhengzhou,China","institution_ids":["https://openalex.org/I169689159"]},{"raw_affiliation_string":"PLA SSF Information Engineering University, Zhengzhou, China","institution_ids":["https://openalex.org/I169689159"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026243783","display_name":"Jiang Wu","orcid":"https://orcid.org/0000-0002-6548-9551"},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiang Wu","raw_affiliation_strings":["PLA SSF Information Engineering University,Zhengzhou,China","PLA SSF Information Engineering University, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"PLA SSF Information Engineering University,Zhengzhou,China","institution_ids":["https://openalex.org/I169689159"]},{"raw_affiliation_string":"PLA SSF Information Engineering University, Zhengzhou, China","institution_ids":["https://openalex.org/I169689159"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100652568","display_name":"Hao Hu","orcid":"https://orcid.org/0000-0003-4888-6368"},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Hu","raw_affiliation_strings":["PLA SSF Information Engineering University,Zhengzhou,China","PLA SSF Information Engineering University, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"PLA SSF Information Engineering University,Zhengzhou,China","institution_ids":["https://openalex.org/I169689159"]},{"raw_affiliation_string":"PLA SSF Information Engineering University, Zhengzhou, China","institution_ids":["https://openalex.org/I169689159"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031071245","display_name":"Zhiqiang Wu","orcid":"https://orcid.org/0000-0001-9055-5680"},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiang Wu","raw_affiliation_strings":["PLA SSF Information Engineering University,Zhengzhou,China","PLA SSF Information Engineering University, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"PLA SSF Information Engineering University,Zhengzhou,China","institution_ids":["https://openalex.org/I169689159"]},{"raw_affiliation_string":"PLA SSF Information Engineering University, Zhengzhou, China","institution_ids":["https://openalex.org/I169689159"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005253519","display_name":"Weigui Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weigui Huang","raw_affiliation_strings":["PLA SSF Information Engineering University,Zhengzhou,China","PLA SSF Information Engineering University, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"PLA SSF Information Engineering University,Zhengzhou,China","institution_ids":["https://openalex.org/I169689159"]},{"raw_affiliation_string":"PLA SSF Information Engineering University, Zhengzhou, China","institution_ids":["https://openalex.org/I169689159"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100757319"],"corresponding_institution_ids":["https://openalex.org/I169689159"],"apc_list":null,"apc_paid":null,"fwci":0.2651,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6137487,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"261","last_page":"267"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9659000039100647,"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"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9643999934196472,"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":0.8873703479766846},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7310996055603027},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.6920953392982483},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6451449990272522},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5673996806144714},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4370272159576416},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3764173984527588},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35703253746032715},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2264358401298523},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15080833435058594}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8873703479766846},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7310996055603027},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.6920953392982483},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6451449990272522},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5673996806144714},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4370272159576416},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3764173984527588},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35703253746032715},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2264358401298523},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15080833435058594},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cog51982.2022.9893651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog51982.2022.9893651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2111959010","https://openalex.org/W2257979135","https://openalex.org/W2749807327","https://openalex.org/W2765302304","https://openalex.org/W2766447205","https://openalex.org/W2888100907","https://openalex.org/W2945850646","https://openalex.org/W2951191893","https://openalex.org/W2982316857","https://openalex.org/W2989847975","https://openalex.org/W2996037775","https://openalex.org/W3006861906","https://openalex.org/W3118210634","https://openalex.org/W3119115629","https://openalex.org/W3122372191","https://openalex.org/W3202938653","https://openalex.org/W6743756900","https://openalex.org/W6744927671","https://openalex.org/W6762639926","https://openalex.org/W6763305696","https://openalex.org/W6772005887","https://openalex.org/W6789083056","https://openalex.org/W6801829772"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"In":[0],"scenarios":[1,69],"with":[2,70],"aleatoric":[3,71],"uncertainties,":[4],"the":[5,13,17,25,31,59,75],"reward":[6,38,63,79,97],"got":[7,50],"by":[8],"an":[9],"agent":[10],"when":[11,95],"executing":[12],"same":[14,18],"action":[15],"in":[16,35,68],"state":[19],"is":[20],"random,":[21],"which":[22,47],"can":[23,48],"reduce":[24],"stability":[26,91],"and":[27,42,65,73,92],"convergence":[28,93],"speed":[29,94],"of":[30,77],"reinforcement":[32,82],"algorithms.":[33],"However,":[34],"most":[36],"scenarios,":[37],"functions":[39,64,67],"have":[40,89],"regularity,":[41],"their":[43],"expectations":[44,80,98],"are":[45],"determined,":[46],"be":[49],"through":[51],"models":[52],"or":[53],"sample":[54],"statistics.":[55],"This":[56],"paper":[57],"discusses":[58],"distribution":[60],"relationship":[61],"between":[62],"value":[66],"uncertainties":[72],"proves":[74],"feasibility":[76],"using":[78,96],"for":[81],"learning.":[83],"Finally,":[84],"experiments":[85],"show":[86],"that":[87],"algorithms":[88],"better":[90],"than":[99],"random":[100],"rewards.":[101]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}