{"id":"https://openalex.org/W4314947447","doi":"https://doi.org/10.1109/cdc51059.2022.9993059","title":"Safe Finite-Time Reinforcement Learning for Pursuit-Evasion Games","display_name":"Safe Finite-Time Reinforcement Learning for Pursuit-Evasion Games","publication_year":2022,"publication_date":"2022-12-06","ids":{"openalex":"https://openalex.org/W4314947447","doi":"https://doi.org/10.1109/cdc51059.2022.9993059"},"language":"en","primary_location":{"id":"doi:10.1109/cdc51059.2022.9993059","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc51059.2022.9993059","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","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 61st Conference on Decision and Control (CDC)","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/A5015440501","display_name":"Nick\u2010Marios T. Kokolakis","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nick-Marios T. Kokolakis","raw_affiliation_strings":["Georgia Institute of Technology,Daniel Guggenheim School of Aerospace Engineering,Atlanta,GA,USA,30332"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Daniel Guggenheim School of Aerospace Engineering,Atlanta,GA,USA,30332","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040301558","display_name":"Kyriakos G. Vamvoudakis","orcid":"https://orcid.org/0000-0003-1978-4848"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyriakos G. Vamvoudakis","raw_affiliation_strings":["Georgia Institute of Technology,Daniel Guggenheim School of Aerospace Engineering,Atlanta,GA,USA,30332"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Daniel Guggenheim School of Aerospace Engineering,Atlanta,GA,USA,30332","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5015440501"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":1.1096,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.79354047,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4022","last_page":"4027"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12158","display_name":"Guidance and Control Systems","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12158","display_name":"Guidance and Control Systems","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9901999831199646,"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/T14083","display_name":"Extremum Seeking Control Systems","score":0.9624999761581421,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/pursuer","display_name":"Pursuer","score":0.9792230129241943},{"id":"https://openalex.org/keywords/pursuit-evasion","display_name":"Pursuit-evasion","score":0.8990926742553711},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8317102193832397},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6449856162071228},{"id":"https://openalex.org/keywords/evasion","display_name":"Evasion (ethics)","score":0.5540689826011658},{"id":"https://openalex.org/keywords/differential-game","display_name":"Differential game","score":0.5497796535491943},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4989912509918213},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.4830551743507385},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.256033718585968},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19761359691619873},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.09385481476783752}],"concepts":[{"id":"https://openalex.org/C2776927521","wikidata":"https://www.wikidata.org/wiki/Q468489","display_name":"Pursuer","level":2,"score":0.9792230129241943},{"id":"https://openalex.org/C2778388243","wikidata":"https://www.wikidata.org/wiki/Q7261573","display_name":"Pursuit-evasion","level":2,"score":0.8990926742553711},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8317102193832397},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6449856162071228},{"id":"https://openalex.org/C2781251061","wikidata":"https://www.wikidata.org/wiki/Q5416089","display_name":"Evasion (ethics)","level":3,"score":0.5540689826011658},{"id":"https://openalex.org/C2779006483","wikidata":"https://www.wikidata.org/wiki/Q1973196","display_name":"Differential game","level":2,"score":0.5497796535491943},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4989912509918213},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.4830551743507385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.256033718585968},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19761359691619873},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.09385481476783752},{"id":"https://openalex.org/C8891405","wikidata":"https://www.wikidata.org/wiki/Q1059","display_name":"Immune system","level":2,"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/C203014093","wikidata":"https://www.wikidata.org/wiki/Q101929","display_name":"Immunology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc51059.2022.9993059","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc51059.2022.9993059","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","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 61st Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320316514","display_name":"Arm","ror":"https://ror.org/04mmhzs81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1988837728","https://openalex.org/W2015113370","https://openalex.org/W2027197837","https://openalex.org/W2053572490","https://openalex.org/W2101746612","https://openalex.org/W2141426220","https://openalex.org/W2162192359","https://openalex.org/W2183469038","https://openalex.org/W2327902530","https://openalex.org/W2411429396","https://openalex.org/W2968945909","https://openalex.org/W2995089744","https://openalex.org/W3013559981","https://openalex.org/W3045857947","https://openalex.org/W3048735518","https://openalex.org/W3102740879","https://openalex.org/W3119933750","https://openalex.org/W3134969796","https://openalex.org/W3184253385","https://openalex.org/W4210554830","https://openalex.org/W4241021229","https://openalex.org/W4294692043","https://openalex.org/W4301018745","https://openalex.org/W4304480072"],"related_works":["https://openalex.org/W1994748888","https://openalex.org/W2904928784","https://openalex.org/W2114317113","https://openalex.org/W2546733891","https://openalex.org/W4253161990","https://openalex.org/W2162909213","https://openalex.org/W2904453786","https://openalex.org/W4287714708","https://openalex.org/W2039546613","https://openalex.org/W3043754713"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"develop":[4],"a":[5,22],"safe":[6],"pursuit-evasion":[7,17,61],"game":[8,18,25],"for":[9,53],"enabling":[10,64],"finite-time":[11,65],"capture":[12,66],"and":[13,56],"optimal":[14],"performance.":[15],"The":[16],"is":[19,50,71],"formulated":[20],"as":[21],"zero-sum":[23],"differential":[24],"wherein":[26],"the":[27,36,39,60,68,80,86,92,95],"pursuer":[28],"seeks":[29],"to":[30,35,42],"minimize":[31],"its":[32],"relative":[33],"distance":[34],"target":[37],"while":[38],"evader":[40],"attempts":[41],"maximize":[43],"it.":[44],"A":[45],"critic-only":[46],"reinforcement":[47],"learning-based":[48],"algorithm":[49],"then":[51],"proposed":[52,96],"learning":[54],"online":[55],"in":[57],"finite":[58],"time":[59],"policies,":[62],"thus":[63],"of":[67,75,94],"evader.":[69],"Safety":[70],"ensured":[72],"by":[73],"means":[74],"barrier":[76],"functions":[77],"associated":[78],"with":[79],"obstacles,":[81],"which":[82],"are":[83],"integrated":[84],"into":[85],"running":[87],"cost.":[88],"Simulation":[89],"results":[90],"illustrate":[91],"efficacy":[93],"approach.":[97]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"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"}