{"id":"https://openalex.org/W2396820603","doi":"https://doi.org/10.4018/ijsir.2016070102","title":"Reinforcement Learning with Particle Swarm Optimization Policy (PSO-P) in Continuous State and Action Spaces","display_name":"Reinforcement Learning with Particle Swarm Optimization Policy (PSO-P) in Continuous State and Action Spaces","publication_year":2016,"publication_date":"2016-05-23","ids":{"openalex":"https://openalex.org/W2396820603","doi":"https://doi.org/10.4018/ijsir.2016070102","mag":"2396820603"},"language":"en","primary_location":{"id":"doi:10.4018/ijsir.2016070102","is_oa":false,"landing_page_url":"https://doi.org/10.4018/ijsir.2016070102","pdf_url":null,"source":{"id":"https://openalex.org/S146254016","display_name":"International Journal of Swarm Intelligence Research","issn_l":"1947-9263","issn":["1947-9263","1947-9271"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Swarm Intelligence Research","raw_type":"journal-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/A5060543628","display_name":"Daniel Hein","orcid":"https://orcid.org/0000-0002-8375-1592"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel Hein","raw_affiliation_strings":["Technische, Universit\u00e4t M\u00fcnchen, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische, Universit\u00e4t M\u00fcnchen, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006415567","display_name":"Alexander Hentschel","orcid":null},"institutions":[{"id":"https://openalex.org/I1325886976","display_name":"Siemens (Germany)","ror":"https://ror.org/059mq0909","country_code":"DE","type":"company","lineage":["https://openalex.org/I1325886976"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander Hentschel","raw_affiliation_strings":["Siemens AG, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Siemens AG, Munich, Germany","institution_ids":["https://openalex.org/I1325886976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002518694","display_name":"Thomas A. Runkler","orcid":"https://orcid.org/0000-0002-5465-198X"},"institutions":[{"id":"https://openalex.org/I1325886976","display_name":"Siemens (Germany)","ror":"https://ror.org/059mq0909","country_code":"DE","type":"company","lineage":["https://openalex.org/I1325886976"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas A. Runkler","raw_affiliation_strings":["Siemens AG, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Siemens AG, Munich, Germany","institution_ids":["https://openalex.org/I1325886976"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035246650","display_name":"Steffen Udluft","orcid":"https://orcid.org/0000-0002-5767-2591"},"institutions":[{"id":"https://openalex.org/I1325886976","display_name":"Siemens (Germany)","ror":"https://ror.org/059mq0909","country_code":"DE","type":"company","lineage":["https://openalex.org/I1325886976"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Steffen Udluft","raw_affiliation_strings":["Siemens AG, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Siemens AG, Munich, Germany","institution_ids":["https://openalex.org/I1325886976"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0915,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.92848136,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"7","issue":"3","first_page":"23","last_page":"42"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9959999918937683,"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":0.9959999918937683,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9915000200271606,"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"}},{"id":"https://openalex.org/T12810","display_name":"Real-time simulation and control systems","score":0.9739000201225281,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7979241013526917},{"id":"https://openalex.org/keywords/particle-swarm-optimization","display_name":"Particle swarm optimization","score":0.7746491432189941},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6659960746765137},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6135488748550415},{"id":"https://openalex.org/keywords/multi-swarm-optimization","display_name":"Multi-swarm optimization","score":0.5096771717071533},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5032865405082703},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.48499223589897156},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4517700672149658},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.44574227929115295},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.41080522537231445},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27752840518951416},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23593896627426147},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17699405550956726}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7979241013526917},{"id":"https://openalex.org/C85617194","wikidata":"https://www.wikidata.org/wiki/Q2072794","display_name":"Particle swarm optimization","level":2,"score":0.7746491432189941},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6659960746765137},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6135488748550415},{"id":"https://openalex.org/C122357587","wikidata":"https://www.wikidata.org/wiki/Q6934508","display_name":"Multi-swarm optimization","level":3,"score":0.5096771717071533},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5032865405082703},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.48499223589897156},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4517700672149658},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.44574227929115295},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.41080522537231445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27752840518951416},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23593896627426147},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17699405550956726},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.4018/ijsir.2016070102","is_oa":false,"landing_page_url":"https://doi.org/10.4018/ijsir.2016070102","pdf_url":null,"source":{"id":"https://openalex.org/S146254016","display_name":"International Journal of Swarm Intelligence Research","issn_l":"1947-9263","issn":["1947-9263","1947-9271"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Swarm Intelligence Research","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:igg:jsir00:v:7:y:2016:i:3:p:23-42","is_oa":false,"landing_page_url":"https://services.igi-global.com/resolvedoi/resolve.aspx?doi=10.4018/IJSIR.2016070102","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W560904894","https://openalex.org/W1515851193","https://openalex.org/W1576278180","https://openalex.org/W1576426930","https://openalex.org/W1631623342","https://openalex.org/W1914583973","https://openalex.org/W1988560433","https://openalex.org/W2002219970","https://openalex.org/W2006278461","https://openalex.org/W2035347224","https://openalex.org/W2073787051","https://openalex.org/W2082489839","https://openalex.org/W2124175081","https://openalex.org/W2137983211","https://openalex.org/W2151425668","https://openalex.org/W2151554678","https://openalex.org/W2152195021","https://openalex.org/W2155353042","https://openalex.org/W2171074980","https://openalex.org/W3015571647","https://openalex.org/W3102923851","https://openalex.org/W3146803896","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2006324351","https://openalex.org/W2965421953","https://openalex.org/W2349895019","https://openalex.org/W2950423922","https://openalex.org/W2116074880","https://openalex.org/W2121780490","https://openalex.org/W2070977815","https://openalex.org/W2137136732","https://openalex.org/W2132113279","https://openalex.org/W2113224065"],"abstract_inverted_index":{"This":[0,61],"article":[1],"introduces":[2],"a":[3,37,78],"model-based":[4],"reinforcement":[5],"learning":[6],"(RL)":[7],"approach":[8,25],"for":[9,40,58,69,104],"continuous":[10],"state":[11,72],"and":[12,74,122],"action":[13,34],"spaces.":[14],"While":[15],"most":[16],"RL":[17,42,88,99],"methods":[18],"try":[19],"to":[20,56],"find":[21],"closed-form":[22],"policies,":[23],"the":[24,93,116],"taken":[26],"here":[27],"employs":[28],"numerical":[29,106],"on-line":[30],"optimization":[31,45,91,107],"of":[32,96,111],"control":[33],"sequences.":[35],"First,":[36],"general":[38],"method":[39],"reformulating":[41],"problems":[43,89],"as":[44],"tasks":[46],"is":[47,54,67,101,113],"provided.":[48],"Subsequently,":[49],"Particle":[50,62],"Swarm":[51,63],"Optimization":[52,64],"(PSO)":[53],"applied":[55],"search":[57],"optimal":[59],"solutions.":[60],"Policy":[65],"(PSO-P)":[66],"effective":[68],"high":[70],"dimensional":[71],"spaces":[73],"does":[75],"not":[76],"require":[77],"priori":[79],"assumptions":[80],"about":[81],"adequate":[82],"policy":[83],"representations.":[84],"Furthermore,":[85],"by":[86],"translating":[87],"into":[90],"tasks,":[92],"rich":[94],"collection":[95],"real-world":[97],"inspired":[98],"benchmarks":[100],"made":[102],"available":[103],"benchmarking":[105],"techniques.":[108],"The":[109],"effectiveness":[110],"PSO-P":[112],"demonstrated":[114],"on":[115],"two":[117],"standard":[118],"benchmarks:":[119],"mountain":[120],"car":[121],"cart":[123],"pole.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}