{"id":"https://openalex.org/W3012783233","doi":"https://doi.org/10.1109/tnnls.2020.2977924","title":"Learning With Stochastic Guidance for Robot Navigation","display_name":"Learning With Stochastic Guidance for Robot Navigation","publication_year":2020,"publication_date":"2020-03-24","ids":{"openalex":"https://openalex.org/W3012783233","doi":"https://doi.org/10.1109/tnnls.2020.2977924","mag":"3012783233","pmid":"https://pubmed.ncbi.nlm.nih.gov/32203029"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2020.2977924","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2020.2977924","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5006960979","display_name":"Linhai Xie","orcid":"https://orcid.org/0000-0001-8593-2277"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Linhai Xie","raw_affiliation_strings":["University of Oxford, Oxford, U.K"],"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, U.K","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035200265","display_name":"Yishu Miao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yishu Miao","raw_affiliation_strings":["MO Intelligence Ltd., Oxford, U.K"],"affiliations":[{"raw_affiliation_string":"MO Intelligence Ltd., Oxford, U.K","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100350760","display_name":"Sen Wang","orcid":"https://orcid.org/0000-0003-1537-8834"},"institutions":[{"id":"https://openalex.org/I32062511","display_name":"Heriot-Watt University","ror":"https://ror.org/04mghma93","country_code":"GB","type":"education","lineage":["https://openalex.org/I32062511"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sen Wang","raw_affiliation_strings":["School of Engineering and Physical Sciences, Heriot-Watt University, Edinburgh, U.K"],"affiliations":[{"raw_affiliation_string":"School of Engineering and Physical Sciences, Heriot-Watt University, Edinburgh, U.K","institution_ids":["https://openalex.org/I32062511"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036811894","display_name":"Phil Blunsom","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Phil Blunsom","raw_affiliation_strings":["University of Oxford, Oxford, U.K"],"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, U.K","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100356891","display_name":"Zhihua Wang","orcid":"https://orcid.org/0000-0003-0413-5327"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhihua Wang","raw_affiliation_strings":["University of Oxford, Oxford, U.K"],"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, U.K","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046822372","display_name":"Changhao Chen","orcid":"https://orcid.org/0000-0002-8341-6399"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Changhao Chen","raw_affiliation_strings":["University of Oxford, Oxford, U.K"],"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, U.K","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060183988","display_name":"Andrew Markham","orcid":"https://orcid.org/0000-0001-5716-3941"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrew Markham","raw_affiliation_strings":["University of Oxford, Oxford, U.K"],"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, U.K","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010637110","display_name":"Niki Trigoni","orcid":"https://orcid.org/0000-0001-6236-9645"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Niki Trigoni","raw_affiliation_strings":["University of Oxford, Oxford, U.K"],"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, U.K","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5006960979"],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":3.8398,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.9445263,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"32","issue":"1","first_page":"166","last_page":"176"},"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9966999888420105,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6856886744499207},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6853628158569336},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6504850387573242},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.628205418586731},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6140308380126953},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5795756578445435},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5442372560501099},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47505971789360046},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.44265085458755493},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.39296454191207886},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1603146493434906},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14504393935203552},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14125049114227295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6856886744499207},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6853628158569336},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6504850387573242},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.628205418586731},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6140308380126953},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5795756578445435},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5442372560501099},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47505971789360046},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.44265085458755493},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.39296454191207886},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1603146493434906},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14504393935203552},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14125049114227295},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tnnls.2020.2977924","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2020.2977924","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:32203029","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32203029","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null},{"id":"pmh:oai:ora.ox.ac.uk:uuid:67c65744-7949-4005-87ad-d987471d170e","is_oa":false,"landing_page_url":"https://ora.ox.ac.uk/objects/uuid:67c65744-7949-4005-87ad-d987471d170e","pdf_url":null,"source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symplectic Elements","raw_type":"Journal article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/14","score":0.5799999833106995,"display_name":"Life below water"}],"awards":[{"id":"https://openalex.org/G2483205037","display_name":null,"funder_award_id":"EP/M019918/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W73143588","https://openalex.org/W2038396847","https://openalex.org/W2046376809","https://openalex.org/W2106667095","https://openalex.org/W2107438106","https://openalex.org/W2117211893","https://openalex.org/W2119717200","https://openalex.org/W2145339207","https://openalex.org/W2151967501","https://openalex.org/W2155027007","https://openalex.org/W2187669537","https://openalex.org/W2187922941","https://openalex.org/W2201581102","https://openalex.org/W2257979135","https://openalex.org/W2283952362","https://openalex.org/W2347074400","https://openalex.org/W2417786368","https://openalex.org/W2518731509","https://openalex.org/W2529658650","https://openalex.org/W2547875792","https://openalex.org/W2554984891","https://openalex.org/W2573470024","https://openalex.org/W2575705757","https://openalex.org/W2601322194","https://openalex.org/W2621133045","https://openalex.org/W2732319713","https://openalex.org/W2748490912","https://openalex.org/W2787259794","https://openalex.org/W2791797404","https://openalex.org/W2795561664","https://openalex.org/W2952264928","https://openalex.org/W2962755817","https://openalex.org/W2962887844","https://openalex.org/W2962957005","https://openalex.org/W2963007936","https://openalex.org/W2963129648","https://openalex.org/W2963351648","https://openalex.org/W2963428623","https://openalex.org/W2963477884","https://openalex.org/W2963639957","https://openalex.org/W2963864421","https://openalex.org/W4206547457","https://openalex.org/W6603031904","https://openalex.org/W6676105031","https://openalex.org/W6677929280","https://openalex.org/W6682569104","https://openalex.org/W6683204974","https://openalex.org/W6684921986","https://openalex.org/W6687448594","https://openalex.org/W6687681856","https://openalex.org/W6695087160","https://openalex.org/W6716474083","https://openalex.org/W6729448088","https://openalex.org/W6729507393","https://openalex.org/W6735944222","https://openalex.org/W6738975087","https://openalex.org/W6740402285"],"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/W2024136090","https://openalex.org/W2964765435","https://openalex.org/W2411867243"],"abstract_inverted_index":{"Due":[0],"to":[1,51,93,98,144],"the":[2,66,70,78,81,88,100,115,136],"sparse":[3],"rewards":[4],"and":[5,55,146,152],"high":[6,26],"degree":[7],"of":[8,25,80,102,109,118,138],"environmental":[9],"variation,":[10],"reinforcement":[11],"learning":[12],"approaches,":[13],"such":[14],"as":[15,106],"deep":[16],"deterministic":[17],"policy":[18],"gradient":[19],"(DDPG),":[20],"are":[21,142],"plagued":[22],"by":[23,43,125],"issues":[24,42],"variance":[27],"when":[28],"applied":[29],"in":[30,69,83],"complex":[31],"real-world":[32],"environments.":[33],"We":[34],"present":[35],"a":[36,45,84,103,119],"new":[37],"framework":[38,82],"for":[39],"overcoming":[40],"these":[41],"incorporating":[44],"stochastic":[46,59,139],"switch,":[47],"allowing":[48],"an":[49],"agent":[50],"choose":[52,92],"between":[53],"high-":[54],"low-variance":[56],"policies.":[57],"The":[58,130],"switch":[60],"can":[61,90,121],"be":[62,122],"jointly":[63],"trained":[64],"with":[65,135],"original":[67],"DDPG":[68,149],"same":[71],"framework.":[72],"In":[73],"this":[74],"article,":[75],"we":[76,141],"demonstrate":[77],"power":[79],"navigation":[85,116,150],"task,":[86],"where":[87],"robot":[89,120],"dynamically":[91],"learn":[94],"through":[95],"exploration":[96],"or":[97],"use":[99],"output":[101],"heuristic":[104],"controller":[105],"guidance.":[107],"Instead":[108],"starting":[110],"from":[111],"completely":[112],"random":[113],"actions,":[114],"capability":[117],"quickly":[123],"bootstrapped":[124],"several":[126],"simple":[127],"independent":[128],"controllers.":[129],"experimental":[131],"results":[132],"show":[133],"that":[134],"aid":[137],"guidance,":[140],"able":[143],"effectively":[145],"efficiently":[147],"train":[148],"policies":[151],"achieve":[153],"significantly":[154],"better":[155],"performance":[156],"than":[157],"state-of-the-art":[158],"baseline":[159],"models.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":9}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}