{"id":"https://openalex.org/W2625858940","doi":"https://doi.org/10.1145/3055635.3056621","title":"Attention-Based Experience Replay in Deep Q-Learning","display_name":"Attention-Based Experience Replay in Deep Q-Learning","publication_year":2017,"publication_date":"2017-02-24","ids":{"openalex":"https://openalex.org/W2625858940","doi":"https://doi.org/10.1145/3055635.3056621","mag":"2625858940"},"language":"en","primary_location":{"id":"doi:10.1145/3055635.3056621","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3055635.3056621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th International Conference on Machine Learning and Computing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/11311/1031983","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075795436","display_name":"Mirza Rami\u010di\u0107","orcid":"https://orcid.org/0000-0002-6302-4515"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mirza Ramicic","raw_affiliation_strings":["Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060263666","display_name":"Andrea Bonarini","orcid":"https://orcid.org/0000-0002-4880-4521"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Bonarini","raw_affiliation_strings":["Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I93860229"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"476","last_page":"481"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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":0.9987999796867371,"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/T10581","display_name":"Neural dynamics and brain function","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9811999797821045,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8999626636505127},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8258116245269775},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.7417251467704773},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7186217904090881},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5617635846138},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5515692234039307},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4865254759788513},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.48466020822525024},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4471486210823059},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43831273913383484},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4357045590877533},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4343600869178772},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.4244289994239807},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.11737963557243347},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09425896406173706}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8999626636505127},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8258116245269775},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.7417251467704773},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7186217904090881},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5617635846138},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5515692234039307},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4865254759788513},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.48466020822525024},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4471486210823059},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43831273913383484},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4357045590877533},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4343600869178772},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.4244289994239807},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.11737963557243347},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09425896406173706},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3055635.3056621","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3055635.3056621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th International Conference on Machine Learning and Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:re.public.polimi.it:11311/1031983","is_oa":true,"landing_page_url":"http://hdl.handle.net/11311/1031983","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:re.public.polimi.it:11311/1031983","is_oa":true,"landing_page_url":"http://hdl.handle.net/11311/1031983","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W223932524","https://openalex.org/W640905404","https://openalex.org/W1515851193","https://openalex.org/W1595483645","https://openalex.org/W1757796397","https://openalex.org/W2006941855","https://openalex.org/W2081543993","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2153432403","https://openalex.org/W2201581102","https://openalex.org/W2526096220","https://openalex.org/W2965017053"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W4225571923","https://openalex.org/W2154399718","https://openalex.org/W3212257828","https://openalex.org/W4321463377","https://openalex.org/W4384574988","https://openalex.org/W2768629321","https://openalex.org/W1914583973"],"abstract_inverted_index":{"Using":[0],"neural":[1],"networks":[2],"as":[3,30,76],"function":[4],"approximators":[5],"in":[6,16,25,132],"temporal":[7],"difference":[8],"reinforcement":[9],"problems":[10],"proved":[11],"to":[12,50,54,57,69,85,118,157,168],"be":[13],"very":[14],"effective":[15],"dealing":[17],"with":[18,87,94,111,151],"high-dimensionality":[19],"of":[20,38,63,114,121,128,148],"input":[21],"state":[22],"space,":[23],"especially":[24],"more":[26,159],"recent":[27],"developments":[28],"such":[29,75],"Deep":[31],"Q-learning.":[32],"These":[33],"approaches":[34],"share":[35],"the":[36,47,61,64,71,92,115,125,129,146,165],"use":[37],"a":[39,51,103,133],"mechanism,":[40],"called":[41,105],"experience":[42,78],"replay,":[43],"that":[44,154],"uniformly":[45],"samples":[46],"previous":[48],"experiences":[49],"memory":[52],"buffer":[53,117],"exploit":[55],"them":[56],"re-learn,":[58],"thus":[59],"improving":[60],"efficiency":[62],"learning":[65,72,130],"process.":[66],"In":[67,98],"order":[68],"increase":[70],"performance,":[73],"techniques":[74],"prioritized":[77,80],"and":[79,89,135],"sampling":[81],"have":[82],"been":[83],"introduced":[84],"deal":[86],"storing":[88],"replaying,":[90],"respectively,":[91],"transitions":[93],"larger":[95],"TD":[96],"error.":[97],"this":[99],"paper,":[100],"we":[101],"present":[102],"concept,":[104],"Attention-Based":[106],"Experience":[107],"REplay":[108],"(ABERE),":[109],"concerned":[110],"selective":[112],"focusing":[113],"replay":[116],"specific":[119],"types":[120],"experiences,":[122],"therefore":[123],"modeling":[124],"behavioral":[126,143],"characteristics":[127,144],"agent":[131],"single":[134],"multi-agent":[136],"environment.":[137],"We":[138],"further":[139],"explore":[140],"how":[141],"different":[142],"influence":[145],"performance":[147],"agents":[149],"faced":[150],"dynamic":[152],"environment":[153],"is":[155],"able":[156],"become":[158],"hostile":[160],"or":[161,171],"benevolent":[162],"by":[163],"changing":[164],"relative":[166],"probability":[167],"get":[169],"positive":[170],"negative":[172],"reinforcement.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}