{"id":"https://openalex.org/W4383108754","doi":"https://doi.org/10.1109/icra48891.2023.10161189","title":"A Continuous Off-Policy Reinforcement Learning Scheme for Optimal Motion Planning in Simply-Connected Workspaces","display_name":"A Continuous Off-Policy Reinforcement Learning Scheme for Optimal Motion Planning in Simply-Connected Workspaces","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383108754","doi":"https://doi.org/10.1109/icra48891.2023.10161189"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10161189","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10161189","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","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/A5001781861","display_name":"Panagiotis Rousseas","orcid":"https://orcid.org/0000-0003-4669-3204"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Panagiotis Rousseas","raw_affiliation_strings":["School of Mechanical Engineering, Control Systems Laboratory, National Technical University of Athens,Greece","School of Mechanical Engineering, Control Systems Laboratory, National Technical University of Athens, Greece"],"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Control Systems Laboratory, National Technical University of Athens,Greece","institution_ids":["https://openalex.org/I174458059"]},{"raw_affiliation_string":"School of Mechanical Engineering, Control Systems Laboratory, National Technical University of Athens, Greece","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020695725","display_name":"Charalampos P. Bechlioulis","orcid":"https://orcid.org/0000-0001-9850-2540"},"institutions":[{"id":"https://openalex.org/I174878644","display_name":"University of Patras","ror":"https://ror.org/017wvtq80","country_code":"GR","type":"education","lineage":["https://openalex.org/I174878644"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Charalampos P. Bechlioulis","raw_affiliation_strings":["University of Patras,Department of Electrical and Computer Engineering","Department of Electrical and Computer Engineering, University of Patras"],"affiliations":[{"raw_affiliation_string":"University of Patras,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I174878644"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Patras","institution_ids":["https://openalex.org/I174878644"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012966309","display_name":"Kostas J. Kyriakopoulos","orcid":"https://orcid.org/0000-0002-1229-3029"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kostas J. Kyriakopoulos","raw_affiliation_strings":["Center of AI & Robotics (CAIR), New York University,Abu Dhabi"],"affiliations":[{"raw_affiliation_string":"Center of AI & Robotics (CAIR), New York University,Abu Dhabi","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5001781861"],"corresponding_institution_ids":["https://openalex.org/I174458059"],"apc_list":null,"apc_paid":null,"fwci":1.1054,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.79605551,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"10247","last_page":"10253"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9976999759674072,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8629657030105591},{"id":"https://openalex.org/keywords/workspace","display_name":"Workspace","score":0.8513211011886597},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6927329301834106},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6628787517547607},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.6318511962890625},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.6104663610458374},{"id":"https://openalex.org/keywords/impossibility","display_name":"Impossibility","score":0.5802760720252991},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.5593791007995605},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5267571806907654},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3364168405532837},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3074384331703186},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22837874293327332},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2114960253238678}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8629657030105591},{"id":"https://openalex.org/C58581272","wikidata":"https://www.wikidata.org/wiki/Q12741163","display_name":"Workspace","level":3,"score":0.8513211011886597},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6927329301834106},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6628787517547607},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.6318511962890625},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.6104663610458374},{"id":"https://openalex.org/C2776261394","wikidata":"https://www.wikidata.org/wiki/Q315562","display_name":"Impossibility","level":2,"score":0.5802760720252991},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.5593791007995605},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5267571806907654},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3364168405532837},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3074384331703186},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22837874293327332},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2114960253238678},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10161189","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10161189","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","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":35,"referenced_works":["https://openalex.org/W1556083071","https://openalex.org/W1904799423","https://openalex.org/W1971086298","https://openalex.org/W1991119064","https://openalex.org/W2030777923","https://openalex.org/W2076738229","https://openalex.org/W2098475019","https://openalex.org/W2106569214","https://openalex.org/W2108286682","https://openalex.org/W2110144538","https://openalex.org/W2126881026","https://openalex.org/W2128990851","https://openalex.org/W2154722715","https://openalex.org/W2155336942","https://openalex.org/W2199171022","https://openalex.org/W2484646121","https://openalex.org/W2557741120","https://openalex.org/W2560504659","https://openalex.org/W2599174273","https://openalex.org/W2890358241","https://openalex.org/W2963469207","https://openalex.org/W3003265341","https://openalex.org/W3005907094","https://openalex.org/W3016507688","https://openalex.org/W3022310485","https://openalex.org/W3035578948","https://openalex.org/W3091360778","https://openalex.org/W3120772201","https://openalex.org/W3131301495","https://openalex.org/W3133407528","https://openalex.org/W3214738088","https://openalex.org/W4206260634","https://openalex.org/W4285189729","https://openalex.org/W6682489740","https://openalex.org/W6780383567"],"related_works":["https://openalex.org/W2384156839","https://openalex.org/W4321602641","https://openalex.org/W1992503747","https://openalex.org/W2371519816","https://openalex.org/W2394251275","https://openalex.org/W2043154226","https://openalex.org/W915072206","https://openalex.org/W4241392912","https://openalex.org/W2369529107","https://openalex.org/W2109948066"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"an":[3,92],"Integral":[4],"Reinforcement":[5],"Learning":[6],"(RL)":[7],"framework":[8],"is":[9,45,81],"employed":[10],"to":[11,83],"provide":[12],"provably":[13],"safe,":[14],"convergent":[15],"and":[16,44,55,68,101],"almost":[17,105],"globally":[18],"optimal":[19],"policies":[20],"in":[21,40,66,95],"a":[22],"novel":[23],"Off-Policy":[24],"Iterative":[25],"method":[26,53,65,94],"for":[27,47],"simply-connected":[28],"workspaces.":[29],"This":[30],"restriction":[31],"stems":[32],"from":[33],"the":[34,64,72,78],"impossibility":[35],"of":[36],"strictly":[37],"global":[38,106],"navigation":[39],"multiply":[41],"connected":[42],"manifolds,":[43],"necessary":[46],"formulating":[48],"continuous":[49],"solutions.":[50],"The":[51],"current":[52],"generalizes":[54],"improves":[56],"upon":[57],"previous":[58,86],"results,":[59],"where":[60],"parametrized":[61],"controllers":[62],"hindered":[63],"scope":[67],"results.":[69],"Through":[70],"enhancing":[71],"traditional":[73],"reactive":[74,87],"paradigm":[75],"with":[76],"RL,":[77],"proposed":[79],"scheme":[80],"demonstrated":[82],"outperform":[84],"both":[85],"methods":[88],"as":[89,91],"well":[90],"RRT*":[93],"path":[96],"length,":[97],"cost":[98],"function":[99],"values":[100],"execution":[102],"times,":[103],"indicating":[104],"optimality.":[107]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}