{"id":"https://openalex.org/W4403936933","doi":"https://doi.org/10.1109/tbdata.2024.3489415","title":"Reward Shaping Based on Optimal-Policy-Free","display_name":"Reward Shaping Based on Optimal-Policy-Free","publication_year":2024,"publication_date":"2024-10-31","ids":{"openalex":"https://openalex.org/W4403936933","doi":"https://doi.org/10.1109/tbdata.2024.3489415"},"language":"en","primary_location":{"id":"doi:10.1109/tbdata.2024.3489415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tbdata.2024.3489415","pdf_url":null,"source":{"id":"https://openalex.org/S2491400915","display_name":"IEEE Transactions on Big Data","issn_l":"2332-7790","issn":["2332-7790","2372-2096"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Big Data","raw_type":"journal-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/A5114472745","display_name":"Jianghui Sang","orcid":"https://orcid.org/0000-0001-7537-6844"},"institutions":[{"id":"https://openalex.org/I92178344","display_name":"Anhui University of Technology","ror":"https://ror.org/02qdtrq21","country_code":"CN","type":"education","lineage":["https://openalex.org/I92178344"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianghui Sang","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University of Technology, Maanshan, China","School of Computer Science and Technology, Anhui University of Technology, MaAnShan, China"],"raw_orcid":"https://orcid.org/0000-0001-7537-6844","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University of Technology, Maanshan, China","institution_ids":["https://openalex.org/I92178344"]},{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University of Technology, MaAnShan, China","institution_ids":["https://openalex.org/I92178344"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100633735","display_name":"Yongli Wang","orcid":"https://orcid.org/0000-0003-2219-067X"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongli Wang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","School of Computer Science and Engineering, Nanjing University of Science And Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-2219-067X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science And Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019761707","display_name":"Zaki Ahmad Khan","orcid":"https://orcid.org/0000-0002-8776-2109"},"institutions":[{"id":"https://openalex.org/I808010","display_name":"University of Worcester","ror":"https://ror.org/00v6s9648","country_code":"GB","type":"education","lineage":["https://openalex.org/I808010"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zaki Ahmad Khan","raw_affiliation_strings":["Department of Computer Science, University of Worcester, Worcester, U.K","Department of computer science, University of Worcester, Worcester, U.K"],"raw_orcid":"https://orcid.org/0000-0002-8776-2109","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Worcester, Worcester, U.K","institution_ids":["https://openalex.org/I808010"]},{"raw_affiliation_string":"Department of computer science, University of Worcester, Worcester, U.K","institution_ids":["https://openalex.org/I808010"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xiaoliang Zhou","orcid":"https://orcid.org/0009-0007-5665-845X"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoliang Zhou","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","School of Computer Science and Engineering, Nanjing University of Science And Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0007-5665-845X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science And Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28137517,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"4","first_page":"1787","last_page":"1798"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.2667999863624573,"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"}},"topics":[{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.2667999863624573,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7139569520950317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7139569520950317}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tbdata.2024.3489415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tbdata.2024.3489415","pdf_url":null,"source":{"id":"https://openalex.org/S2491400915","display_name":"IEEE Transactions on Big Data","issn_l":"2332-7790","issn":["2332-7790","2372-2096"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Big Data","raw_type":"journal-article"},{"id":"pmh:oai:wrap.eprints.org:14426","is_oa":false,"landing_page_url":"https://orcid.org/0000-0001-7537-6844","pdf_url":null,"source":{"id":"https://openalex.org/S4306400296","display_name":"Worcester Research and Publications (University of Worcester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I808010","host_organization_name":"University of Worcester","host_organization_lineage":["https://openalex.org/I808010"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3160330032","display_name":null,"funder_award_id":"61941113","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W2030729450","https://openalex.org/W2061902782","https://openalex.org/W2095564494","https://openalex.org/W2143958939","https://openalex.org/W2202549229","https://openalex.org/W2962800562","https://openalex.org/W2963523627","https://openalex.org/W3036446966","https://openalex.org/W3039969618","https://openalex.org/W3080644389","https://openalex.org/W3095746859","https://openalex.org/W3123742938","https://openalex.org/W3127356132","https://openalex.org/W3174282399","https://openalex.org/W3202546516","https://openalex.org/W4213286046","https://openalex.org/W4230962939","https://openalex.org/W4318159260","https://openalex.org/W4318586076","https://openalex.org/W4361770561","https://openalex.org/W4380235474","https://openalex.org/W4382449740","https://openalex.org/W4384161790","https://openalex.org/W4385270306","https://openalex.org/W4385300629","https://openalex.org/W4385729101","https://openalex.org/W4386783362","https://openalex.org/W6604948569","https://openalex.org/W6638088447","https://openalex.org/W6674884181","https://openalex.org/W6682205418","https://openalex.org/W6691215711","https://openalex.org/W6696891444","https://openalex.org/W6739917289","https://openalex.org/W6749859622","https://openalex.org/W6756303580","https://openalex.org/W6757469721","https://openalex.org/W6764976746","https://openalex.org/W6777179611","https://openalex.org/W6784307559","https://openalex.org/W6784694379","https://openalex.org/W6784856447","https://openalex.org/W6785204124","https://openalex.org/W6785380959","https://openalex.org/W6797702751","https://openalex.org/W6801968024","https://openalex.org/W6802659552","https://openalex.org/W6803972293","https://openalex.org/W6844194202","https://openalex.org/W6852418670"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Existing":[0],"research":[1],"on":[2,8,65,73,84,121,169,176],"potential-based":[3],"reward":[4],"shaping":[5],"(PBRS)":[6],"relies":[7],"optimal":[9,17,40,45,51,75],"policy":[10,18,41,52],"in":[11,26,97,102,151,156],"Markov":[12],"decision":[13],"process":[14],"(MDP)":[15],"where":[16],"is":[19,32,53,106,142,167],"regarded":[20],"as":[21,81,108],"the":[22,38,43,50,71,74,94,98,131,134,138,146,162,186],"ground":[23],"truth.":[24],"However,":[25],"some":[27],"practical":[28],"application":[29],"scenarios,":[30],"there":[31],"an":[33],"extrapolation":[34],"error":[35],"challenge":[36],"between":[37],"computed":[39],"and":[42,100,179],"real-world":[44],"policy.":[46,76],"At":[47],"this":[48,57,89,126,170],"time,":[49],"unreliable.":[54],"To":[55],"address":[56],"challenge,":[58],"we":[59],"design":[60],"a":[61,85,103,109,117],"Reward":[62],"Shaping":[63],"based":[64],"Optimal-Policy-Free":[66],"to":[67,144],"get":[68],"rid":[69],"of":[70,133],"dependence":[72],"We":[77],"view":[78],"reinforcement":[79],"learning":[80,119],"probabilistic":[82],"inference":[83,90],"directed":[86,122,135,139,171],"graph.":[87,136],"Essentially,":[88],"propagates":[91],"information":[92],"from":[93],"rewarding":[95],"states":[96],"MDP":[99],"results":[101],"function":[104,111,155],"which":[105,166],"leveraged":[107],"potential":[110,154],"for":[112],"PBRS.":[113],"Our":[114],"approach":[115,184],"utilizes":[116],"contrastive":[118],"technique":[120,127],"graph":[123,140,172],"Laplacian.":[124,173],"Here,":[125],"does":[128],"not":[129],"change":[130],"structure":[132],"Then,":[137],"Laplacian":[141],"used":[143],"approximate":[145],"true":[147],"state":[148],"transition":[149],"matrix":[150],"MDP.":[152],"The":[153,174],"PBRS":[157],"can":[158],"be":[159],"learned":[160],"through":[161],"message":[163],"passing":[164],"mechanism":[165],"built":[168],"experiments":[175],"Atari,":[177],"MuJoCo":[178],"MiniWorld":[180],"show":[181],"that":[182],"our":[183],"outperforms":[185],"competitive":[187],"algorithms.":[188]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}