{"id":"https://openalex.org/W3010996978","doi":"https://doi.org/10.1109/cdc40024.2019.9029286","title":"Transforming Policy via Reward Advancement","display_name":"Transforming Policy via Reward Advancement","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3010996978","doi":"https://doi.org/10.1109/cdc40024.2019.9029286","mag":"3010996978"},"language":"en","primary_location":{"id":"doi:10.1109/cdc40024.2019.9029286","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc40024.2019.9029286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 58th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5078615235","display_name":"Guojun Wu","orcid":"https://orcid.org/0000-0002-7910-2813"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guojun Wu","raw_affiliation_strings":["Worcester Polytechnic Institute (WPI), USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute (WPI), USA","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100630059","display_name":"Yanhua Li","orcid":"https://orcid.org/0000-0001-8972-503X"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanhua Li","raw_affiliation_strings":["Worcester Polytechnic Institute (WPI), USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute (WPI), USA","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106731907","display_name":"Jun Luo","orcid":"https://orcid.org/0000-0002-2032-0381"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Luo","raw_affiliation_strings":["Machine Intelligence Center (Hong Kong), Lenovo Group Limited"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Intelligence Center (Hong Kong), Lenovo Group Limited","institution_ids":["https://openalex.org/I4210156165"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.476,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.63455868,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"99","issue":null,"first_page":"4609","last_page":"4614"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12617","display_name":"Energy, Environment, and Transportation Policies","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/2105","display_name":"Renewable Energy, Sustainability and the Environment"},"field":{"id":"https://openalex.org/fields/21","display_name":"Energy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12617","display_name":"Energy, Environment, and Transportation Policies","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/2105","display_name":"Renewable Energy, Sustainability and the Environment"},"field":{"id":"https://openalex.org/fields/21","display_name":"Energy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10698","display_name":"Transportation Planning and Optimization","score":0.9884999990463257,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9840999841690063,"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/bounded-rationality","display_name":"Bounded rationality","score":0.6852506995201111},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.6510459184646606},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5515230298042297},{"id":"https://openalex.org/keywords/rationality","display_name":"Rationality","score":0.52999347448349},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5038613677024841},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.4234328866004944},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3799895644187927},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.32070785760879517},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.28001686930656433},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27554798126220703},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2453785538673401},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.17962989211082458},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.15281039476394653}],"concepts":[{"id":"https://openalex.org/C58694771","wikidata":"https://www.wikidata.org/wiki/Q814385","display_name":"Bounded rationality","level":2,"score":0.6852506995201111},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6510459184646606},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5515230298042297},{"id":"https://openalex.org/C201717286","wikidata":"https://www.wikidata.org/wiki/Q938185","display_name":"Rationality","level":2,"score":0.52999347448349},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5038613677024841},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.4234328866004944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3799895644187927},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.32070785760879517},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.28001686930656433},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27554798126220703},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2453785538673401},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.17962989211082458},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.15281039476394653},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc40024.2019.9029286","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc40024.2019.9029286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 58th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W64088143","https://openalex.org/W640944534","https://openalex.org/W1777239053","https://openalex.org/W2054505936","https://openalex.org/W2097498341","https://openalex.org/W2098774185","https://openalex.org/W2112738128","https://openalex.org/W2117675763","https://openalex.org/W2121863487","https://openalex.org/W2130750514","https://openalex.org/W2167041463","https://openalex.org/W2290104316","https://openalex.org/W2609650878","https://openalex.org/W2782637183","https://openalex.org/W2907455543","https://openalex.org/W2944211469","https://openalex.org/W2963590100","https://openalex.org/W3003540860","https://openalex.org/W3103379718","https://openalex.org/W4214717370","https://openalex.org/W4233777236","https://openalex.org/W6620783027","https://openalex.org/W6638088447","https://openalex.org/W6674664616","https://openalex.org/W6674884181","https://openalex.org/W6677555207","https://openalex.org/W6696380822","https://openalex.org/W6736495777"],"related_works":["https://openalex.org/W1667647204","https://openalex.org/W2404647514","https://openalex.org/W4247536566","https://openalex.org/W4388260134","https://openalex.org/W2489352369","https://openalex.org/W2801172480","https://openalex.org/W4297440579","https://openalex.org/W187959850","https://openalex.org/W4300099835","https://openalex.org/W4299547270"],"abstract_inverted_index":{"Many":[0],"real":[1],"world":[2],"human":[3,47],"behaviors":[4,57],"can":[5,58,123],"be":[6,59],"characterized":[7],"as":[8,14],"sequential":[9],"decision":[10],"making":[11],"processes,":[12],"such":[13],"urban":[15],"travelers'":[16],"choices":[17,26],"of":[18,86,154],"transport":[19],"modes":[20],"and":[21,73,110,152,163],"routes":[22],"[1].":[23],"Differing":[24],"from":[25,95,172],"controlled":[27],"by":[28],"machines,":[29],"which":[30],"in":[31],"general":[32],"follows":[33],"perfect":[34],"rationality":[35,54],"to":[36,134,143],"adopt":[37],"the":[38,84,92,125,137,145,150],"policy":[39,94,100,113,127,146],"with":[40,140],"highest":[41],"reward,":[42],"studies":[43],"have":[44],"revealed":[45],"that":[46,90,106,122],"agents":[48],"make":[49],"sub-optimal":[50],"decisions":[51],"under":[52],"bounded":[53],"[2].":[55],"Such":[56],"modeled":[60],"using":[61,159],"maximum":[62],"causal":[63],"entropy":[64],"(MCE)":[65],"principle":[66],"[3].":[67],"In":[68],"this":[69],"paper,":[70],"we":[71,130],"define":[72],"investigate":[74],"a":[75,97,111,164],"novel":[76],"reward":[77,81,88,120,156],"transformation":[78],"problem":[79],"(namely,":[80],"advancement):":[82],"Recovering":[83],"range":[85],"additional":[87,119,138],"functions":[89,121],"transform":[91],"agent's":[93],"\u03c0oto":[96],"predefined":[98],"target":[99,112],"\u03c0tunder":[101],"MCE":[102],"principle.":[103],"We":[104,148],"show":[105],"given":[107],"an":[108,132],"MDP":[109],"\u03c0t,":[114],"there":[115],"are":[116],"infinite":[117],"many":[118],"achieve":[124],"desired":[126],"transformation.":[128,147],"Moreover,":[129],"propose":[131],"algorithm":[133],"further":[135],"extract":[136],"rewards":[139],"minimum":[141],"\"cost\"":[142],"implement":[144],"demonstrated":[149],"correctness":[151],"accuracy":[153],"our":[155],"advancement":[157],"solution":[158],"both":[160],"synthetic":[161],"data":[162,171],"largescale":[165],"(6":[166],"months)":[167],"passenger-level":[168],"public":[169],"transit":[170],"Shenzhen,":[173],"China.":[174]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}