{"id":"https://openalex.org/W4389666137","doi":"https://doi.org/10.1109/iros55552.2023.10342259","title":"Reinforcement Learning Under Probabilistic Spatio-Temporal Constraints with Time Windows","display_name":"Reinforcement Learning Under Probabilistic Spatio-Temporal Constraints with Time Windows","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389666137","doi":"https://doi.org/10.1109/iros55552.2023.10342259"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10342259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342259","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5018068424","display_name":"Xiaoshan Lin","orcid":"https://orcid.org/0000-0002-8913-5539"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiaoshan Lin","raw_affiliation_strings":["University of Minnesota,Department of Aerospace Engineering and Mechanics,Minneapolis,MN,55455"],"affiliations":[{"raw_affiliation_string":"University of Minnesota,Department of Aerospace Engineering and Mechanics,Minneapolis,MN,55455","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083059964","display_name":"Abbasali Koochakzadeh","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abbasali Koochakzadeh","raw_affiliation_strings":["Purdue University,Department of Electrical and Computer Engineering,West Lafayette,IN,47907"],"affiliations":[{"raw_affiliation_string":"Purdue University,Department of Electrical and Computer Engineering,West Lafayette,IN,47907","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041762786","display_name":"Yasin Yaz\u0131c\u0131o\u011flu","orcid":"https://orcid.org/0000-0001-6957-6831"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yasin Yaz\u0131c\u0131o\u011flu","raw_affiliation_strings":["Northeastern University,Department of Mechanical and Industrial Engineering,Boston,MA,02115"],"affiliations":[{"raw_affiliation_string":"Northeastern University,Department of Mechanical and Industrial Engineering,Boston,MA,02115","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053550436","display_name":"Derya Aksaray","orcid":"https://orcid.org/0000-0003-4236-9116"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Derya Aksaray","raw_affiliation_strings":["Northeastern University,Department of Electrical and Computer Engineering,Boston,MA,02115"],"affiliations":[{"raw_affiliation_string":"Northeastern University,Department of Electrical and Computer Engineering,Boston,MA,02115","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5018068424"],"corresponding_institution_ids":["https://openalex.org/I130238516"],"apc_list":null,"apc_paid":null,"fwci":0.3491,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67352002,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"8680","last_page":"8686"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9865999817848206,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10603","display_name":"Smart Grid Energy Management","score":0.9858999848365784,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7477148771286011},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7396722435951233},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7238975167274475},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5285101532936096},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3218218684196472}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7477148771286011},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7396722435951233},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7238975167274475},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5285101532936096},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3218218684196472}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10342259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342259","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1084912964","display_name":null,"funder_award_id":"HR0011-21-2-0015","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W41554520","https://openalex.org/W2097838240","https://openalex.org/W2291637985","https://openalex.org/W2903775008","https://openalex.org/W2946040040","https://openalex.org/W2963525569","https://openalex.org/W2963575966","https://openalex.org/W2964219844","https://openalex.org/W2964352321","https://openalex.org/W2966735560","https://openalex.org/W3006844914","https://openalex.org/W3046384803","https://openalex.org/W3048735518","https://openalex.org/W3121342653","https://openalex.org/W3128176255","https://openalex.org/W3129402851","https://openalex.org/W4206497039","https://openalex.org/W4318983719","https://openalex.org/W4389666137","https://openalex.org/W6682367392","https://openalex.org/W6855822357"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"We":[0,97,108],"propose":[1],"an":[2],"automata-theoretic":[3],"approach":[4,47],"for":[5,93],"reinforcement":[6],"learning":[7],"(RL)":[8],"under":[9,25],"complex":[10],"spatio-temporal":[11],"constraints":[12],"with":[13],"time":[14],"windows.":[15],"The":[16],"problem":[17],"is":[18,58],"formulated":[19],"using":[20],"a":[21,26,49,68,86,114,117],"Markov":[22],"decision":[23],"process":[24],"bounded":[27,63],"temporal":[28,64,138],"logic":[29,65,139],"constraint.":[30],"Different":[31],"from":[32],"existing":[33],"RL":[34],"methods":[35],"that":[36,134],"can":[37],"eventually":[38],"learn":[39],"optimal":[40],"policies":[41],"satisfying":[42],"such":[43],"constraints,":[44],"our":[45],"proposed":[46],"enforces":[48],"desired":[50],"probability":[51,104],"of":[52,88,105],"constraint":[53,66,106],"satisfaction":[54],"throughout":[55],"learning.":[56],"This":[57],"achieved":[59],"by":[60],"translating":[61],"the":[62,77,82,102,120],"into":[67],"total":[69],"automaton":[70],"and":[71,90,131],"avoiding":[72],"\u201cunsafe\u201d":[73],"actions":[74],"based":[75],"on":[76,101],"available":[78],"prior":[79],"information":[80],"regarding":[81],"transition":[83,95],"probabilities,":[84],"i.e.,":[85],"pair":[87],"upper":[89],"lower":[91],"bounds":[92],"each":[94],"probability.":[96],"provide":[98,110],"theoretical":[99],"guarantees":[100],"resulting":[103],"satisfaction.":[107],"also":[109],"numerical":[111],"results":[112],"in":[113],"scenario":[115],"where":[116],"robot":[118],"explores":[119],"environment":[121],"to":[122],"discover":[123],"high-reward":[124],"regions":[125],"while":[126],"fulfilling":[127],"some":[128],"periodic":[129],"pick-up":[130],"delivery":[132],"tasks":[133],"are":[135],"encoded":[136],"as":[137],"constraints.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}