{"id":"https://openalex.org/W4308236842","doi":"https://doi.org/10.1109/icip46576.2022.9897349","title":"Improving Generalization of Reinforcement Learning Using a Bilinear Policy Network","display_name":"Improving Generalization of Reinforcement Learning Using a Bilinear Policy Network","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4308236842","doi":"https://doi.org/10.1109/icip46576.2022.9897349"},"language":"en","primary_location":{"id":"doi:10.1109/icip46576.2022.9897349","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897349","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Image Processing (ICIP)","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/A5030374805","display_name":"Fen Fang","orcid":"https://orcid.org/0000-0002-3834-4795"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Fen Fang","raw_affiliation_strings":["A*STAR,Institute for Infocomm Research,Singapore","Institute for Infocomm Research, A*STAR, Singapore"],"affiliations":[{"raw_affiliation_string":"A*STAR,Institute for Infocomm Research,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080546069","display_name":"Wenyu Liang","orcid":"https://orcid.org/0000-0003-0278-2723"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wenyu Liang","raw_affiliation_strings":["A*STAR,Institute for Infocomm Research,Singapore","Institute for Infocomm Research, A*STAR, Singapore"],"affiliations":[{"raw_affiliation_string":"A*STAR,Institute for Infocomm Research,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047015759","display_name":"Yan Wu","orcid":"https://orcid.org/0000-0003-4293-9430"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yan Wu","raw_affiliation_strings":["A*STAR,Institute for Infocomm Research,Singapore","Institute for Infocomm Research, A*STAR, Singapore"],"affiliations":[{"raw_affiliation_string":"A*STAR,Institute for Infocomm Research,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052143634","display_name":"Qianli Xu","orcid":"https://orcid.org/0000-0003-0105-5903"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Qianli Xu","raw_affiliation_strings":["A*STAR,Institute for Infocomm Research,Singapore","Institute for Infocomm Research, A*STAR, Singapore"],"affiliations":[{"raw_affiliation_string":"A*STAR,Institute for Infocomm Research,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077258552","display_name":"Joo\u2010Hwee Lim","orcid":"https://orcid.org/0000-0002-4103-3824"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Joo-Hwee Lim","raw_affiliation_strings":["A*STAR,Institute for Infocomm Research,Singapore","Institute for Infocomm Research, A*STAR, Singapore","School of Computer Science and Engineering, NTU, Singapore"],"affiliations":[{"raw_affiliation_string":"A*STAR,Institute for Infocomm Research,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"School of Computer Science and Engineering, NTU, Singapore","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5030374805"],"corresponding_institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"],"apc_list":null,"apc_paid":null,"fwci":0.2078,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.42313079,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"22","issue":null,"first_page":"991","last_page":"995"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9937999844551086,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9898999929428101,"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/generalization","display_name":"Generalization","score":0.769290030002594},{"id":"https://openalex.org/keywords/bilinear-interpolation","display_name":"Bilinear interpolation","score":0.7680765390396118},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7153830528259277},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.713416576385498},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.6120148301124573},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6033262610435486},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5644708275794983},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.49964451789855957},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.48692286014556885},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4678930342197418},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4604068994522095},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45006856322288513},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12319883704185486},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09541985392570496}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.769290030002594},{"id":"https://openalex.org/C205203396","wikidata":"https://www.wikidata.org/wiki/Q612143","display_name":"Bilinear interpolation","level":2,"score":0.7680765390396118},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7153830528259277},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.713416576385498},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6120148301124573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6033262610435486},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5644708275794983},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.49964451789855957},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.48692286014556885},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4678930342197418},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4604068994522095},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45006856322288513},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12319883704185486},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09541985392570496},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip46576.2022.9897349","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897349","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Image Processing (ICIP)","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":25,"referenced_works":["https://openalex.org/W1560724230","https://openalex.org/W1606858007","https://openalex.org/W1821963137","https://openalex.org/W1898560071","https://openalex.org/W2104657103","https://openalex.org/W2105880865","https://openalex.org/W2107726111","https://openalex.org/W2124175081","https://openalex.org/W2124386111","https://openalex.org/W2201581102","https://openalex.org/W2479109623","https://openalex.org/W2531563875","https://openalex.org/W2580726517","https://openalex.org/W2754931255","https://openalex.org/W2756270667","https://openalex.org/W2779475642","https://openalex.org/W2907503094","https://openalex.org/W3095104908","https://openalex.org/W3195977921","https://openalex.org/W3205934217","https://openalex.org/W4298857966","https://openalex.org/W6637967152","https://openalex.org/W6687681856","https://openalex.org/W6746684068","https://openalex.org/W6787959036"],"related_works":["https://openalex.org/W2165589608","https://openalex.org/W2487162673","https://openalex.org/W3093557575","https://openalex.org/W2793211469","https://openalex.org/W2354231916","https://openalex.org/W3182767856","https://openalex.org/W2949152769","https://openalex.org/W4372354731","https://openalex.org/W2162140574","https://openalex.org/W2807634898"],"abstract_inverted_index":{"In":[0],"deep":[1],"reinforcement":[2],"learning":[3],"(DRL),":[4],"the":[5,31,40,46,59,111,147,155],"agent":[6],"is":[7,20,37,52,99,118],"usually":[8],"trained":[9],"on":[10,120,128],"seen":[11],"environments":[12,27],"by":[13,154],"optimizing":[14],"a":[15,62,75,95,125],"policy":[16,41,97,116],"network.":[17,157],"However,":[18],"it":[19,81],"difficult":[21],"to":[22,25,101,107],"be":[23,152],"generalized":[24],"unseen":[26],"properly,":[28],"even":[29],"when":[30],"environmental":[32],"variations":[33],"are":[34],"insignificant.":[35],"This":[36],"partly":[38],"because":[39],"network":[42,98,117],"cannot":[43],"effectively":[44],"learn":[45],"representation":[47,103],"of":[48,110,149],"visual":[49],"difference":[50,86],"that":[51,146],"subtle":[53,85],"among":[54,88],"highly":[55,89],"similar":[56,90],"states":[57],"in":[58,74,92],"environments.":[60],"Because":[61],"bilinear":[63,96,115],"structured":[64],"model":[65],"containing":[66],"two":[67],"feature":[68,72],"extractors":[69],"allows":[70],"pairwise":[71],"interactions":[73],"translation-ally":[76],"invariant":[77],"manner":[78],"which":[79],"makes":[80],"particularly":[82],"useful":[83],"for":[84,131],"recognition":[87],"states,":[91],"this":[93],"work,":[94],"employed":[100],"enhance":[102],"learning,":[104],"and":[105,135],"thus":[106],"improve":[108],"generalization":[109,148],"DRL.":[112],"The":[113,142],"proposed":[114,156],"tested":[119],"various":[121],"DRL":[122,150],"task,":[123],"including":[124],"control":[126],"task":[127],"path":[129],"planning":[130],"active":[132],"object":[133],"detection,":[134],"Grid":[136],"World,":[137],"an":[138],"AI":[139],"game":[140],"task.":[141],"test":[143],"results":[144],"show":[145],"can":[151],"improved":[153]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}