{"id":"https://openalex.org/W3089426894","doi":"https://doi.org/10.1109/ijcnn48605.2020.9206608","title":"True Online TD(\u03bb)-Replay An Efficient Model-free Planning with Full Replay","display_name":"True Online TD(\u03bb)-Replay An Efficient Model-free Planning with Full Replay","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3089426894","doi":"https://doi.org/10.1109/ijcnn48605.2020.9206608","mag":"3089426894"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9206608","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9206608","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","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/A5054979460","display_name":"Abdulrahman Altahhan","orcid":"https://orcid.org/0000-0003-1133-7744"},"institutions":[{"id":"https://openalex.org/I84027002","display_name":"Leeds Beckett University","ror":"https://ror.org/02xsh5r57","country_code":"GB","type":"education","lineage":["https://openalex.org/I84027002"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Abdulrahman Altahhan","raw_affiliation_strings":["School of Built Environment, Engineering and Computing, Leeds Beckett University, Leeds, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Built Environment, Engineering and Computing, Leeds Beckett University, Leeds, UK","institution_ids":["https://openalex.org/I84027002"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5054979460"],"corresponding_institution_ids":["https://openalex.org/I84027002"],"apc_list":null,"apc_paid":null,"fwci":0.1301,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.55233433,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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/T11685","display_name":"Zebrafish Biomedical Research Applications","score":0.9779000282287598,"subfield":{"id":"https://openalex.org/subfields/1307","display_name":"Cell Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9710000157356262,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8489583730697632},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7040407061576843},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6508463621139526},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.55744868516922},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.504428505897522},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4896166920661926},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47482237219810486},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4667867422103882},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.4587258994579315},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.43186450004577637},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.065733402967453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8489583730697632},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7040407061576843},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6508463621139526},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.55744868516922},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.504428505897522},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4896166920661926},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47482237219810486},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4667867422103882},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.4587258994579315},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.43186450004577637},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.065733402967453},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9206608","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9206608","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.whiterose.ac.uk:168203","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Proceedings Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1576452626","https://openalex.org/W1758031947","https://openalex.org/W1870822514","https://openalex.org/W2066759535","https://openalex.org/W2082480549","https://openalex.org/W2121863487","https://openalex.org/W2139418546","https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2159752377","https://openalex.org/W2200297111","https://openalex.org/W2269274350","https://openalex.org/W2295042734","https://openalex.org/W2735162671","https://openalex.org/W2766688757","https://openalex.org/W2767187792","https://openalex.org/W2772721022","https://openalex.org/W2796621129","https://openalex.org/W2888561335","https://openalex.org/W2950517718","https://openalex.org/W2962731213","https://openalex.org/W2963794592","https://openalex.org/W3136620014","https://openalex.org/W3195835426","https://openalex.org/W4231109964","https://openalex.org/W4288638482","https://openalex.org/W4295231058","https://openalex.org/W6638058698","https://openalex.org/W6639088027","https://openalex.org/W6745540326","https://openalex.org/W6746809867","https://openalex.org/W6757795073","https://openalex.org/W6793907288"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2000169967","https://openalex.org/W2112883198"],"abstract_inverted_index":{"In":[0,66],"this":[1,131],"paper,":[2],"we":[3,68],"present":[4],"a":[5,98,109,134],"new":[6,51],"reinforcement":[7],"learning":[8],"prediction":[9],"method":[10,52,72,93,132],"that":[11,36,45,70,112,117],"extends":[12],"the":[13,16,34,89,127],"capabilities":[14,90],"of":[15,28,91,130],"true":[17,54],"online":[18,32,55],"TD(\u03bb)":[19],"to":[20,24,62],"allow":[21],"an":[22],"agent":[23],"efficiently":[25],"replay":[26,64],"all":[27],"its":[29,63],"past":[30],"experience,":[31],"in":[33,59],"sequence":[35],"they":[37],"appear":[38],"with.":[39],"We":[40,87],"demonstrate":[41,69],"that,":[42],"for":[43,133],"problems":[44],"benefit":[46],"from":[47,121],"experience":[48],"replay,":[49],"our":[50,71,92],"outperforms":[53,73],"TD(\u03bb),":[56],"albeit":[57],"quadratic":[58,78],"complexity":[60,79],"due":[61],"capabilities.":[65],"addition,":[67],"other":[74,138],"methods":[75],"with":[76,103,115],"similar":[77],"such":[80],"as":[81],"Dyna":[82],"Planning":[83],"and":[84,107],"TD(0)-Replay":[85],"algorithms.":[86],"showcase":[88],"on":[94,108],"two":[95],"benchmarking":[96],"domains,":[97],"random":[99],"walk":[100],"problem":[101],"tested":[102,114],"simple":[104],"binary":[105],"features":[106,116],"myoelectric":[110],"domain":[111],"is":[113],"are":[118],"deeply":[119],"extracted":[120],"sEMG":[122],"signals.":[123],"Experimental":[124],"results":[125],"confirm":[126],"particular":[128],"suitability":[129],"deep":[135],"architecture":[136],"over":[137],"methods.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}