{"id":"https://openalex.org/W4387140978","doi":"https://doi.org/10.3390/robotics12050133","title":"An Advisor-Based Architecture for a Sample-Efficient Training of Autonomous Navigation Agents with Reinforcement Learning","display_name":"An Advisor-Based Architecture for a Sample-Efficient Training of Autonomous Navigation Agents with Reinforcement Learning","publication_year":2023,"publication_date":"2023-09-28","ids":{"openalex":"https://openalex.org/W4387140978","doi":"https://doi.org/10.3390/robotics12050133"},"language":"en","primary_location":{"id":"doi:10.3390/robotics12050133","is_oa":true,"landing_page_url":"https://doi.org/10.3390/robotics12050133","pdf_url":"https://www.mdpi.com/2218-6581/12/5/133/pdf?version=1695898794","source":{"id":"https://openalex.org/S4210232487","display_name":"Robotics","issn_l":"2218-6581","issn":["2218-6581"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2218-6581/12/5/133/pdf?version=1695898794","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030666586","display_name":"Rukshan Wijesinghe","orcid":"https://orcid.org/0000-0002-4003-6337"},"institutions":[{"id":"https://openalex.org/I195740183","display_name":"University of Moratuwa","ror":"https://ror.org/0491f5305","country_code":"LK","type":"education","lineage":["https://openalex.org/I195740183"]}],"countries":["LK"],"is_corresponding":true,"raw_author_name":"Rukshan Darshana Wijesinghe","raw_affiliation_strings":["CODEGEN QBITS LAB, University of Moratuwa, Moratuwa 10400, Sri Lanka","Department of Electronic and Telecommunication Engineering, Faculty of Engineering, University of Moratuwa, Moratuwa 10400, Sri Lanka"],"raw_orcid":"https://orcid.org/0000-0002-4003-6337","affiliations":[{"raw_affiliation_string":"CODEGEN QBITS LAB, University of Moratuwa, Moratuwa 10400, Sri Lanka","institution_ids":["https://openalex.org/I195740183"]},{"raw_affiliation_string":"Department of Electronic and Telecommunication Engineering, Faculty of Engineering, University of Moratuwa, Moratuwa 10400, Sri Lanka","institution_ids":["https://openalex.org/I195740183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055449884","display_name":"Dumindu Tissera","orcid":"https://orcid.org/0000-0002-7461-0165"},"institutions":[{"id":"https://openalex.org/I195740183","display_name":"University of Moratuwa","ror":"https://ror.org/0491f5305","country_code":"LK","type":"education","lineage":["https://openalex.org/I195740183"]}],"countries":["LK"],"is_corresponding":false,"raw_author_name":"Dumindu Tissera","raw_affiliation_strings":["CODEGEN QBITS LAB, University of Moratuwa, Moratuwa 10400, Sri Lanka","Department of Electronic and Telecommunication Engineering, Faculty of Engineering, University of Moratuwa, Moratuwa 10400, Sri Lanka"],"raw_orcid":"https://orcid.org/0000-0002-7461-0165","affiliations":[{"raw_affiliation_string":"CODEGEN QBITS LAB, University of Moratuwa, Moratuwa 10400, Sri Lanka","institution_ids":["https://openalex.org/I195740183"]},{"raw_affiliation_string":"Department of Electronic and Telecommunication Engineering, Faculty of Engineering, University of Moratuwa, Moratuwa 10400, Sri Lanka","institution_ids":["https://openalex.org/I195740183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104175401","display_name":"Mihira Kasun Vithanage","orcid":null},"institutions":[{"id":"https://openalex.org/I195740183","display_name":"University of Moratuwa","ror":"https://ror.org/0491f5305","country_code":"LK","type":"education","lineage":["https://openalex.org/I195740183"]}],"countries":["LK"],"is_corresponding":false,"raw_author_name":"Mihira Kasun Vithanage","raw_affiliation_strings":["CODEGEN QBITS LAB, University of Moratuwa, Moratuwa 10400, Sri Lanka","Department of Computational Mathematics, Faculty of Information Technology, University of Moratuwa, Moratuwa 10400, Sri Lanka"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CODEGEN QBITS LAB, University of Moratuwa, Moratuwa 10400, Sri Lanka","institution_ids":["https://openalex.org/I195740183"]},{"raw_affiliation_string":"Department of Computational Mathematics, Faculty of Information Technology, University of Moratuwa, Moratuwa 10400, Sri Lanka","institution_ids":["https://openalex.org/I195740183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047184449","display_name":"Alex Xavier","orcid":"https://orcid.org/0000-0003-4094-0681"},"institutions":[{"id":"https://openalex.org/I195740183","display_name":"University of Moratuwa","ror":"https://ror.org/0491f5305","country_code":"LK","type":"education","lineage":["https://openalex.org/I195740183"]}],"countries":["LK"],"is_corresponding":false,"raw_author_name":"Alex Xavier","raw_affiliation_strings":["CODEGEN QBITS LAB, University of Moratuwa, Moratuwa 10400, Sri Lanka","Department of Computer Science and Engineering, Faculty of Engineering, University of Moratuwa, Moratuwa 10400, Sri Lanka"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CODEGEN QBITS LAB, University of Moratuwa, Moratuwa 10400, Sri Lanka","institution_ids":["https://openalex.org/I195740183"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Faculty of Engineering, University of Moratuwa, Moratuwa 10400, Sri Lanka","institution_ids":["https://openalex.org/I195740183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085751708","display_name":"Subha Fernando","orcid":"https://orcid.org/0000-0002-2621-5291"},"institutions":[{"id":"https://openalex.org/I195740183","display_name":"University of Moratuwa","ror":"https://ror.org/0491f5305","country_code":"LK","type":"education","lineage":["https://openalex.org/I195740183"]}],"countries":["LK"],"is_corresponding":false,"raw_author_name":"Subha Fernando","raw_affiliation_strings":["CODEGEN QBITS LAB, University of Moratuwa, Moratuwa 10400, Sri Lanka","Department of Computational Mathematics, Faculty of Information Technology, University of Moratuwa, Moratuwa 10400, Sri Lanka"],"raw_orcid":"https://orcid.org/0000-0002-2621-5291","affiliations":[{"raw_affiliation_string":"CODEGEN QBITS LAB, University of Moratuwa, Moratuwa 10400, Sri Lanka","institution_ids":["https://openalex.org/I195740183"]},{"raw_affiliation_string":"Department of Computational Mathematics, Faculty of Information Technology, University of Moratuwa, Moratuwa 10400, Sri Lanka","institution_ids":["https://openalex.org/I195740183"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035344274","display_name":"Jayathu G. Samarawickrama","orcid":null},"institutions":[{"id":"https://openalex.org/I195740183","display_name":"University of Moratuwa","ror":"https://ror.org/0491f5305","country_code":"LK","type":"education","lineage":["https://openalex.org/I195740183"]}],"countries":["LK"],"is_corresponding":false,"raw_author_name":"Jayathu Samarawickrama","raw_affiliation_strings":["CODEGEN QBITS LAB, University of Moratuwa, Moratuwa 10400, Sri Lanka","Department of Electronic and Telecommunication Engineering, Faculty of Engineering, University of Moratuwa, Moratuwa 10400, Sri Lanka"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CODEGEN QBITS LAB, University of Moratuwa, Moratuwa 10400, Sri Lanka","institution_ids":["https://openalex.org/I195740183"]},{"raw_affiliation_string":"Department of Electronic and Telecommunication Engineering, Faculty of Engineering, University of Moratuwa, Moratuwa 10400, Sri Lanka","institution_ids":["https://openalex.org/I195740183"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5030666586"],"corresponding_institution_ids":["https://openalex.org/I195740183"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12461936,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":"5","first_page":"133","last_page":"133"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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":0.8747507333755493},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6996487379074097},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6796858906745911},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.6784020662307739},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6774994134902954},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6577423810958862},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5008492469787598},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45949462056159973},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.44673630595207214},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.4379422962665558},{"id":"https://openalex.org/keywords/intelligent-agent","display_name":"Intelligent agent","score":0.41307318210601807},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3877888321876526}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8747507333755493},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6996487379074097},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6796858906745911},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.6784020662307739},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6774994134902954},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6577423810958862},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5008492469787598},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45949462056159973},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.44673630595207214},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.4379422962665558},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.41307318210601807},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3877888321876526},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/robotics12050133","is_oa":true,"landing_page_url":"https://doi.org/10.3390/robotics12050133","pdf_url":"https://www.mdpi.com/2218-6581/12/5/133/pdf?version=1695898794","source":{"id":"https://openalex.org/S4210232487","display_name":"Robotics","issn_l":"2218-6581","issn":["2218-6581"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:02b5d1b10b9b413f9ee2dfb50be6796c","is_oa":true,"landing_page_url":"https://doaj.org/article/02b5d1b10b9b413f9ee2dfb50be6796c","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Robotics, Vol 12, Iss 5, p 133 (2023)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2218-6581/12/5/133/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/robotics12050133","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Robotics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/robotics12050133","is_oa":true,"landing_page_url":"https://doi.org/10.3390/robotics12050133","pdf_url":"https://www.mdpi.com/2218-6581/12/5/133/pdf?version=1695898794","source":{"id":"https://openalex.org/S4210232487","display_name":"Robotics","issn_l":"2218-6581","issn":["2218-6581"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320325939","display_name":"University of Moratuwa","ror":"https://ror.org/0491f5305"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4387140978.pdf"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W1931877416","https://openalex.org/W1977655452","https://openalex.org/W1991446466","https://openalex.org/W2017957151","https://openalex.org/W2018629084","https://openalex.org/W2080360626","https://openalex.org/W2082511574","https://openalex.org/W2100787464","https://openalex.org/W2124267516","https://openalex.org/W2135912307","https://openalex.org/W2145339207","https://openalex.org/W2172968643","https://openalex.org/W2173248099","https://openalex.org/W2257979135","https://openalex.org/W2260756217","https://openalex.org/W2522489477","https://openalex.org/W2575705757","https://openalex.org/W2618398196","https://openalex.org/W2746553466","https://openalex.org/W2787938642","https://openalex.org/W2788862220","https://openalex.org/W2907916537","https://openalex.org/W2954115742","https://openalex.org/W2962872206","https://openalex.org/W2963019567","https://openalex.org/W2963099939","https://openalex.org/W2963129648","https://openalex.org/W2963428623","https://openalex.org/W2963544079","https://openalex.org/W2999713046","https://openalex.org/W2999862950","https://openalex.org/W3020984444","https://openalex.org/W3036472058","https://openalex.org/W3036551067","https://openalex.org/W3039116038","https://openalex.org/W3039772337","https://openalex.org/W3087055389","https://openalex.org/W3122928565","https://openalex.org/W3123348991","https://openalex.org/W3125606138","https://openalex.org/W3127756416","https://openalex.org/W3154791684","https://openalex.org/W3186035148","https://openalex.org/W3190947292","https://openalex.org/W3198729202","https://openalex.org/W3202183201","https://openalex.org/W4214717370","https://openalex.org/W4309308064","https://openalex.org/W6677067356","https://openalex.org/W6682972110","https://openalex.org/W6683195989","https://openalex.org/W6684205842","https://openalex.org/W6696324988"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2877093712","https://openalex.org/W2116157560","https://openalex.org/W4310614650"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,15,43,55,69,72,114,180],"artificial":[3],"intelligence":[4],"have":[5],"enabled":[6],"reinforcement":[7],"learning":[8,62,83],"(RL)":[9],"agents":[10,66,121],"to":[11,39,99,117,122,168],"exceed":[12],"human-level":[13],"performance":[14,23,134,166],"various":[16,169],"gaming":[17],"tasks.":[18],"However,":[19],"despite":[20],"the":[21,89,93,101,127,133,139,154,159,164,176,181,186,190],"state-of-the-art":[22],"demonstrated":[24],"by":[25,91],"model-free":[26],"RL":[27,65],"algorithms,":[28],"they":[29,173],"suffer":[30],"from":[31],"high":[32],"sample":[33,102,160],"complexity.":[34,103],"Hence,":[35],"it":[36],"is":[37,53,67],"uncommon":[38],"find":[40],"their":[41],"applications":[42],"robotics,":[44],"autonomous":[45,119],"navigation,":[46],"and":[47,143],"self-driving,":[48],"as":[49],"gathering":[50],"many":[51],"samples":[52],"impractical":[54],"real-world":[56,73],"hardware":[57],"systems.":[58],"Therefore,":[59],"developing":[60],"sample-efficient":[61],"algorithms":[63],"for":[64],"crucial":[68],"deploying":[70],"them":[71],"tasks":[74],"without":[75,162],"sacrificing":[76],"performance.":[77],"This":[78],"paper":[79],"presents":[80],"an":[81,107,112,151],"advisor-based":[82],"algorithm,":[84],"incorporating":[85,150],"prior":[86],"knowledge":[87],"into":[88,153],"training":[90,155,194],"modifying":[92],"deep":[94],"deterministic":[95],"policy":[96],"gradient":[97],"algorithm":[98],"reduce":[100],"Also,":[104,172],"we":[105],"propose":[106],"effective":[108],"method":[109],"of":[110,129,135,141],"employing":[111],"advisor":[113,152],"data":[115,182],"collection":[116,183],"train":[118],"navigation":[120],"maneuver":[123],"physical":[124,144],"platforms,":[125],"minimizing":[126],"risk":[128],"collision.":[130],"We":[131],"analyze":[132],"our":[136],"methods":[137],"with":[138],"support":[140],"simulation":[142],"experimental":[145],"setups.":[146],"Experiments":[147],"reveal":[148],"that":[149,175],"phase":[156],"significantly":[157],"reduces":[158],"complexity":[161],"compromising":[163],"agent\u2019s":[165,187],"compared":[167],"benchmark":[170],"approaches.":[171],"show":[174],"advisor\u2019s":[177],"constant":[178],"involvement":[179,192],"process":[184],"diminishes":[185],"performance,":[188],"while":[189],"limited":[191],"makes":[193],"more":[195],"effective.":[196]},"counts_by_year":[],"updated_date":"2026-01-22T23:29:09.771500","created_date":"2025-10-10T00:00:00"}