{"id":"https://openalex.org/W4404194227","doi":"https://doi.org/10.1017/s0269888924000092","title":"Reinforcement actor-critic learning as a rehearsal in MicroRTS","display_name":"Reinforcement actor-critic learning as a rehearsal in MicroRTS","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404194227","doi":"https://doi.org/10.1017/s0269888924000092"},"language":"en","primary_location":{"id":"doi:10.1017/s0269888924000092","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s0269888924000092","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/E739944836D9FF0F542F2356466D35BC/S0269888924000092a.pdf/div-class-title-reinforcement-actor-critic-learning-as-a-rehearsal-in-microrts-div.pdf","source":{"id":"https://openalex.org/S137506714","display_name":"The Knowledge Engineering Review","issn_l":"0269-8889","issn":["0269-8889","1469-8005"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Knowledge Engineering Review","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/E739944836D9FF0F542F2356466D35BC/S0269888924000092a.pdf/div-class-title-reinforcement-actor-critic-learning-as-a-rehearsal-in-microrts-div.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114572982","display_name":"Shiron Manandhar","orcid":null},"institutions":[{"id":"https://openalex.org/I44854399","display_name":"University of Southern Mississippi","ror":"https://ror.org/0270vfa57","country_code":"US","type":"education","lineage":["https://openalex.org/I4210141039","https://openalex.org/I44854399"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiron Manandhar","raw_affiliation_strings":["School of Computing Sciences and Computer Engineering, University of Southern Mississippi, Hattiesburg, MS 39406, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing Sciences and Computer Engineering, University of Southern Mississippi, Hattiesburg, MS 39406, USA","institution_ids":["https://openalex.org/I44854399"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025954824","display_name":"Bikramjit Banerjee","orcid":"https://orcid.org/0000-0001-7999-0307"},"institutions":[{"id":"https://openalex.org/I44854399","display_name":"University of Southern Mississippi","ror":"https://ror.org/0270vfa57","country_code":"US","type":"education","lineage":["https://openalex.org/I4210141039","https://openalex.org/I44854399"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bikramjit Banerjee","raw_affiliation_strings":["School of Computing Sciences and Computer Engineering, University of Southern Mississippi, Hattiesburg, MS 39406, USA"],"raw_orcid":"https://orcid.org/0000-0001-7999-0307","affiliations":[{"raw_affiliation_string":"School of Computing Sciences and Computer Engineering, University of Southern Mississippi, Hattiesburg, MS 39406, USA","institution_ids":["https://openalex.org/I44854399"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5025954824"],"corresponding_institution_ids":["https://openalex.org/I44854399"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17100903,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"39","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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":0.9988999962806702,"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/T14011","display_name":"Elevator Systems and Control","score":0.9805999994277954,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9463000297546387,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.7306839227676392},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.5641303658485413},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.49773815274238586},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.4346778392791748},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.3625873923301697},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.35607922077178955},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.2706172466278076},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.20960694551467896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17605221271514893}],"concepts":[{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.7306839227676392},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.5641303658485413},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.49773815274238586},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.4346778392791748},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3625873923301697},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.35607922077178955},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2706172466278076},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.20960694551467896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17605221271514893}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1017/s0269888924000092","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s0269888924000092","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/E739944836D9FF0F542F2356466D35BC/S0269888924000092a.pdf/div-class-title-reinforcement-actor-critic-learning-as-a-rehearsal-in-microrts-div.pdf","source":{"id":"https://openalex.org/S137506714","display_name":"The Knowledge Engineering Review","issn_l":"0269-8889","issn":["0269-8889","1469-8005"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Knowledge Engineering Review","raw_type":"journal-article"},{"id":"pmh:oai:aquila.usm.edu:masters_theses-1979","is_oa":false,"landing_page_url":"https://aquila.usm.edu/masters_theses/914","pdf_url":null,"source":{"id":"https://openalex.org/S4306402529","display_name":"Aquila Digital Community (University of Southern Mississippi)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I44854399","host_organization_name":"University of Southern Mississippi","host_organization_lineage":["https://openalex.org/I44854399"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Master's Theses","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1017/s0269888924000092","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s0269888924000092","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/E739944836D9FF0F542F2356466D35BC/S0269888924000092a.pdf/div-class-title-reinforcement-actor-critic-learning-as-a-rehearsal-in-microrts-div.pdf","source":{"id":"https://openalex.org/S137506714","display_name":"The Knowledge Engineering Review","issn_l":"0269-8889","issn":["0269-8889","1469-8005"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Knowledge Engineering Review","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404194227.pdf","grobid_xml":"https://content.openalex.org/works/W4404194227.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W149149418","https://openalex.org/W1492974543","https://openalex.org/W1507321583","https://openalex.org/W1750339092","https://openalex.org/W1777239053","https://openalex.org/W1867465928","https://openalex.org/W2026615874","https://openalex.org/W2064675550","https://openalex.org/W2098487995","https://openalex.org/W2119717200","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2166798247","https://openalex.org/W2167086559","https://openalex.org/W2188365844","https://openalex.org/W2292533394","https://openalex.org/W2395963869","https://openalex.org/W2626914210","https://openalex.org/W2792745106","https://openalex.org/W2951486153","https://openalex.org/W2963729301","https://openalex.org/W2982316857","https://openalex.org/W3093593979","https://openalex.org/W3093962059","https://openalex.org/W3202329902","https://openalex.org/W4205504069","https://openalex.org/W4214717370","https://openalex.org/W4299335686","https://openalex.org/W4312309732","https://openalex.org/W4387394758","https://openalex.org/W6633869120","https://openalex.org/W6686581360","https://openalex.org/W6751540476","https://openalex.org/W6769022465"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Abstract":[0],"Real-time":[1],"strategy":[2,180],"(RTS)":[3],"games":[4],"have":[5],"provided":[6],"a":[7,26,30,40,49,82,114,123,157,175,178],"fertile":[8],"ground":[9],"for":[10,81,113,135],"AI":[11],"research":[12],"with":[13,126,177],"notable":[14],"recent":[15],"successes":[16],"based":[17,74],"on":[18,39,53,92,106],"deep":[19],"reinforcement":[20,46],"learning":[21,47],"(RL).":[22],"However,":[23],"RL":[24,75,84,138],"remains":[25],"data-hungry":[27],"approach":[28],"featuring":[29],"high":[31],"sample":[32,41],"complexity.":[33],"In":[34],"this":[35],"paper,":[36],"we":[37,78],"focus":[38],"complexity":[42],"reduction":[43],"technique":[44],"called":[45,86],"as":[48,139],"rehearsal":[50],"(RLaR)":[51],"and":[52,61],"the":[54,69,93,96,107,168],"RTS":[55],"game":[56],"of":[57,71,117,128,171],"MicroRTS":[58,143],"to":[59,101,156],"formulate":[60,79],"evaluate":[62],"it.":[63],"RLaR":[64,100,150],"has":[65],"been":[66],"formulated":[67],"in":[68,142,174],"context":[70],"action-value":[72],"function":[73,120],"before.":[76],"Here,":[77],"it":[80,110],"different":[83],"framework,":[85],"actor-critic":[87,97],"RL.":[88],"We":[89],"show":[90],"that":[91,121,127,149,159],"one":[94],"hand":[95],"framework":[98],"allows":[99],"be":[102],"much":[103],"simpler,":[104],"but":[105],"other":[108],"hand,":[109],"leaves":[111],"room":[112],"key":[115],"component":[116],"RLaR\u2013a":[118],"prediction":[119],"relates":[122],"learner\u2019s":[124],"observations":[125],"its":[129],"opponent.":[130],"This":[131,165],"function,":[132],"when":[133],"leveraged":[134],"exploration,":[136],"accelerates":[137],"our":[140],"experiments":[141,146],"show.":[144],"Further":[145],"provide":[147],"evidence":[148],"may":[151],"reduce":[152],"actor":[153],"noise":[154],"compared":[155],"variant":[158],"does":[160],"not":[161],"utilize":[162],"RLaR\u2019s":[163,172],"exploration.":[164],"study":[166],"provides":[167],"first":[169],"evaluation":[170],"efficacy":[173],"domain":[176],"large":[179],"space.":[181]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}