{"id":"https://openalex.org/W7125974495","doi":"https://doi.org/10.1109/smc58881.2025.11342748","title":"Dynamic Incentive Design via Reinforcement Learning Stochastic Control Optimization","display_name":"Dynamic Incentive Design via Reinforcement Learning Stochastic Control Optimization","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125974495","doi":"https://doi.org/10.1109/smc58881.2025.11342748"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11342748","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342748","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":"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/A5124063952","display_name":"Angela Li","orcid":null},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Angela Li","raw_affiliation_strings":["Stony Brook University,Applied Mathematics and Physics,Stony Brook,NY"],"affiliations":[{"raw_affiliation_string":"Stony Brook University,Applied Mathematics and Physics,Stony Brook,NY","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060996710","display_name":"Kevin C. W. Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Chen","raw_affiliation_strings":["Amazon.com, Inc.,New York,NY"],"affiliations":[{"raw_affiliation_string":"Amazon.com, Inc.,New York,NY","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093271268","display_name":"Kun Bao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210146398","display_name":"Minerals Technologies (United States)","ror":"https://ror.org/04hg6v996","country_code":"US","type":"company","lineage":["https://openalex.org/I4210146398"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kun Bao","raw_affiliation_strings":["Uber Technologies, Inc.,New York,NY"],"affiliations":[{"raw_affiliation_string":"Uber Technologies, Inc.,New York,NY","institution_ids":["https://openalex.org/I4210146398"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124142381","display_name":"Cheng Li","orcid":null},"institutions":[{"id":"https://openalex.org/I19772626","display_name":"Yeshiva University","ror":"https://ror.org/045x93337","country_code":"US","type":"education","lineage":["https://openalex.org/I19772626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cheng Li","raw_affiliation_strings":["Yeshiva University,Katz School of Science and Health,New York,NY"],"affiliations":[{"raw_affiliation_string":"Yeshiva University,Katz School of Science and Health,New York,NY","institution_ids":["https://openalex.org/I19772626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116925576","display_name":"Chengkun Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I19772626","display_name":"Yeshiva University","ror":"https://ror.org/045x93337","country_code":"US","type":"education","lineage":["https://openalex.org/I19772626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chengkun Yao","raw_affiliation_strings":["Yeshiva University,Katz School of Science and Health,New York,NY"],"affiliations":[{"raw_affiliation_string":"Yeshiva University,Katz School of Science and Health,New York,NY","institution_ids":["https://openalex.org/I19772626"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100432958","display_name":"David Li","orcid":"https://orcid.org/0000-0002-6401-4263"},"institutions":[{"id":"https://openalex.org/I19772626","display_name":"Yeshiva University","ror":"https://ror.org/045x93337","country_code":"US","type":"education","lineage":["https://openalex.org/I19772626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Li","raw_affiliation_strings":["Yeshiva University,Katz School of Science and Health,New York,NY"],"affiliations":[{"raw_affiliation_string":"Yeshiva University,Katz School of Science and Health,New York,NY","institution_ids":["https://openalex.org/I19772626"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5124063952"],"corresponding_institution_ids":["https://openalex.org/I59553526"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74799525,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5451","last_page":"5456"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13553","display_name":"Age of Information Optimization","score":0.14820000529289246,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T13553","display_name":"Age of Information Optimization","score":0.14820000529289246,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10328","display_name":"Supply Chain and Inventory Management","score":0.13379999995231628,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.08290000259876251,"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":0.7544999718666077},{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.6527000069618225},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.5368000268936157},{"id":"https://openalex.org/keywords/incentive","display_name":"Incentive","score":0.4839000105857849},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.4641000032424927},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.4447999894618988},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.41920000314712524},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.40939998626708984}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7544999718666077},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7250999808311462},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.6527000069618225},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.5368000268936157},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.49889999628067017},{"id":"https://openalex.org/C29122968","wikidata":"https://www.wikidata.org/wiki/Q1414816","display_name":"Incentive","level":2,"score":0.4839000105857849},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.4641000032424927},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.4447999894618988},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.41920000314712524},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.40939998626708984},{"id":"https://openalex.org/C137631369","wikidata":"https://www.wikidata.org/wiki/Q7617831","display_name":"Stochastic programming","level":2,"score":0.39969998598098755},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.3977000117301941},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.3822999894618988},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.3808000087738037},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.34619998931884766},{"id":"https://openalex.org/C138551086","wikidata":"https://www.wikidata.org/wiki/Q842271","display_name":"Marginal utility","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11342748","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342748","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1680189815","https://openalex.org/W2145339207","https://openalex.org/W2146868725","https://openalex.org/W2563416506","https://openalex.org/W2909452395","https://openalex.org/W2921327094","https://openalex.org/W2947191413","https://openalex.org/W3014136593","https://openalex.org/W3027406032","https://openalex.org/W3123937330","https://openalex.org/W3158945149","https://openalex.org/W3175635117","https://openalex.org/W4391216344","https://openalex.org/W4409156321"],"related_works":[],"abstract_inverted_index":{"We":[0,76],"propose":[1],"a":[2,69,87],"reinforcement-aware":[3],"stochastic":[4],"control":[5],"framework":[6,40],"for":[7,94],"real-time":[8],"reward":[9,92],"optimization":[10],"in":[11],"sharing":[12],"economy":[13],"platforms.":[14,97],"Unlike":[15],"traditional":[16],"static":[17],"incentive":[18,74],"schemes,":[19],"our":[20],"model":[21],"dynamically":[22],"allocates":[23],"incentives":[24],"by":[25],"integrating":[26],"belief-driven":[27],"user":[28],"behavior":[29],"modeling,":[30],"Nash":[31],"equilibrium":[32],"assumptions,":[33,80],"and":[34,53,83],"constrained":[35],"utility":[36],"maximization.":[37],"The":[38],"core":[39],"unifies":[41],"dynamic":[42],"programming":[43],"with":[44],"reinforcement":[45],"learning":[46],"(RL)":[47],"approximations":[48],"to":[49,63],"handle":[50],"partial":[51],"observability":[52],"large-scale":[54],"deployment.":[55],"A":[56],"novel":[57],"pricing-based":[58],"calibration":[59],"method":[60],"is":[61],"introduced":[62],"quantify":[64],"the":[65],"marginal":[66],"value":[67],"of":[68],"successful":[70],"transaction,":[71],"enabling":[72],"budget-aligned":[73],"strategies.":[75],"further":[77],"address":[78],"theoretical":[79],"computational":[81],"complexity,":[82],"practical":[84],"implementation,":[85],"providing":[86],"scalable":[88],"path":[89],"toward":[90],"intelligent":[91],"systems":[93],"real-world":[95],"digital":[96]},"counts_by_year":[],"updated_date":"2026-01-29T23:17:01.242718","created_date":"2026-01-29T00:00:00"}