{"id":"https://openalex.org/W3122272697","doi":"https://doi.org/10.1109/ssrr50563.2020.9292603","title":"Learning Spatial Search using Submodular Inverse Reinforcement Learning","display_name":"Learning Spatial Search using Submodular Inverse Reinforcement Learning","publication_year":2020,"publication_date":"2020-11-04","ids":{"openalex":"https://openalex.org/W3122272697","doi":"https://doi.org/10.1109/ssrr50563.2020.9292603","mag":"3122272697"},"language":"en","primary_location":{"id":"doi:10.1109/ssrr50563.2020.9292603","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssrr50563.2020.9292603","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)","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/A5059192195","display_name":"Jijie Wu","orcid":"https://orcid.org/0000-0003-1250-0689"},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Ji-Jie Wu","raw_affiliation_strings":["Mathematics Department, National Central University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Mathematics Department, National Central University, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039241771","display_name":"Kuo-Shih Tseng","orcid":"https://orcid.org/0000-0002-7818-5821"},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kuo-Shih Tseng","raw_affiliation_strings":["Mathematics Department, National Central University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Mathematics Department, National Central University, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5059192195"],"corresponding_institution_ids":["https://openalex.org/I22265921"],"apc_list":null,"apc_paid":null,"fwci":0.2651,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65348806,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"518","issue":null,"first_page":"7","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9991000294685364,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9991000294685364,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980000257492065,"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/T12288","display_name":"Optimization and Search Problems","score":0.9958999752998352,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/submodular-set-function","display_name":"Submodular set function","score":0.8702330589294434},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.761852502822876},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6202269792556763},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5211741328239441},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.49746039509773254},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.468749076128006},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.44116321206092834},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41989535093307495},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.35227513313293457},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25344938039779663},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24831339716911316}],"concepts":[{"id":"https://openalex.org/C178621042","wikidata":"https://www.wikidata.org/wiki/Q7631710","display_name":"Submodular set function","level":2,"score":0.8702330589294434},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.761852502822876},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6202269792556763},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5211741328239441},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.49746039509773254},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.468749076128006},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.44116321206092834},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41989535093307495},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35227513313293457},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25344938039779663},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24831339716911316},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ssrr50563.2020.9292603","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssrr50563.2020.9292603","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)","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":22,"referenced_works":["https://openalex.org/W1680189815","https://openalex.org/W1929981607","https://openalex.org/W2051228319","https://openalex.org/W2098774185","https://openalex.org/W2145339207","https://openalex.org/W2163605009","https://openalex.org/W2215252637","https://openalex.org/W2257979135","https://openalex.org/W2413963660","https://openalex.org/W2434014514","https://openalex.org/W2574299761","https://openalex.org/W2586783934","https://openalex.org/W2618530766","https://openalex.org/W2911239729","https://openalex.org/W2963277051","https://openalex.org/W2963409832","https://openalex.org/W3012264108","https://openalex.org/W3021174677","https://openalex.org/W3092357259","https://openalex.org/W3115952594","https://openalex.org/W6640443443","https://openalex.org/W6674884181"],"related_works":["https://openalex.org/W1595919516","https://openalex.org/W2945022594","https://openalex.org/W2194604332","https://openalex.org/W4379619607","https://openalex.org/W1989453388","https://openalex.org/W2922450688","https://openalex.org/W4313349366","https://openalex.org/W3141561286","https://openalex.org/W2390782349","https://openalex.org/W1510637526"],"abstract_inverted_index":{"Finding":[0],"an":[1],"optimal":[2],"search":[3,10,19,29,35,50,61],"path":[4],"is":[5,11,24],"a":[6,25,40],"NP-hard":[7],"problem.":[8],"Since":[9],"one":[12],"of":[13,34,58,65,67],"human":[14,22],"central":[15],"activities,":[16],"learning":[17,44],"spatial":[18],"behavior":[20],"from":[21],"operators":[23],"way":[26],"to":[27,47],"solve":[28],"problems.":[30],"Utilizing":[31],"the":[32,56,59,68],"submodularity":[33],"problems,":[36],"this":[37],"research":[38],"proposes":[39],"submodular":[41],"inverse":[42],"reinforcement":[43],"(SIRL)":[45],"algorithm":[46],"learn":[48],"humans'":[49],"behavior.":[51],"The":[52],"experiments":[53],"demonstrate":[54],"that":[55,64],"performance":[57],"learned":[60],"paths":[62],"outperform":[63],"state":[66],"art":[69],"approaches":[70],"(e.g.,":[71],"MaxEnt":[72],"IRL":[73],"and":[74],"DIRL).":[75]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}