{"id":"https://openalex.org/W4382449266","doi":"https://doi.org/10.3389/fnbot.2023.1127642","title":"Map-based experience replay: a memory-efficient solution to catastrophic forgetting in reinforcement learning","display_name":"Map-based experience replay: a memory-efficient solution to catastrophic forgetting in reinforcement learning","publication_year":2023,"publication_date":"2023-06-27","ids":{"openalex":"https://openalex.org/W4382449266","doi":"https://doi.org/10.3389/fnbot.2023.1127642","pmid":"https://pubmed.ncbi.nlm.nih.gov/37440981"},"language":"en","primary_location":{"id":"doi:10.3389/fnbot.2023.1127642","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fnbot.2023.1127642","pdf_url":"https://www.frontiersin.org/articles/10.3389/fnbot.2023.1127642/pdf","source":{"id":"https://openalex.org/S115606517","display_name":"Frontiers in Neurorobotics","issn_l":"1662-5218","issn":["1662-5218"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Neurorobotics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/articles/10.3389/fnbot.2023.1127642/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042086036","display_name":"Muhammad Burhan Hafez","orcid":"https://orcid.org/0000-0003-1670-8962"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]},{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Muhammad Burhan Hafez","raw_affiliation_strings":["Knowledge Technology Research Group, Department of Informatics, University of Hamburg, Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Knowledge Technology Research Group, Department of Informatics, University of Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037453647","display_name":"Tilman Immisch","orcid":null},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]},{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tilman Immisch","raw_affiliation_strings":["Knowledge Technology Research Group, Department of Informatics, University of Hamburg, Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Knowledge Technology Research Group, Department of Informatics, University of Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055686810","display_name":"Tom Weber","orcid":"https://orcid.org/0000-0002-7560-4963"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]},{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tom Weber","raw_affiliation_strings":["Knowledge Technology Research Group, Department of Informatics, University of Hamburg, Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Knowledge Technology Research Group, Department of Informatics, University of Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033486668","display_name":"Stefan Wermter","orcid":"https://orcid.org/0000-0003-1343-4775"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]},{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Wermter","raw_affiliation_strings":["Knowledge Technology Research Group, Department of Informatics, University of Hamburg, Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Knowledge Technology Research Group, Department of Informatics, University of Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5042086036"],"corresponding_institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"],"apc_list":{"value":2950,"currency":"USD","value_usd":2950},"apc_paid":{"value":2950,"currency":"USD","value_usd":2950},"fwci":2.4851,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.91172208,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"17","issue":null,"first_page":"1127642","last_page":"1127642"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9923999905586243,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9921000003814697,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.9478973150253296},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8344079256057739},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7391030788421631},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.7127707600593567},{"id":"https://openalex.org/keywords/shuffling","display_name":"Shuffling","score":0.4766698181629181},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4438621997833252},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.0817626416683197}],"concepts":[{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.9478973150253296},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8344079256057739},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7391030788421631},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.7127707600593567},{"id":"https://openalex.org/C167927819","wikidata":"https://www.wikidata.org/wiki/Q1930567","display_name":"Shuffling","level":2,"score":0.4766698181629181},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4438621997833252},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.0817626416683197},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3389/fnbot.2023.1127642","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fnbot.2023.1127642","pdf_url":"https://www.frontiersin.org/articles/10.3389/fnbot.2023.1127642/pdf","source":{"id":"https://openalex.org/S115606517","display_name":"Frontiers in Neurorobotics","issn_l":"1662-5218","issn":["1662-5218"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Neurorobotics","raw_type":"journal-article"},{"id":"pmid:37440981","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37440981","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":"Frontiers in neurorobotics","raw_type":null},{"id":"pmh:oai:eprints.soton.ac.uk:496188","is_oa":true,"landing_page_url":"http://doi.org/10.3389/fnbot.2023.1127642>).","pdf_url":"https://eprints.soton.ac.uk/496188/1/fnbot-17-1127642.pdf","source":{"id":"https://openalex.org/S4306401019","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:pubmedcentral.nih.gov:10333526","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10333526","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10333526/pdf/fnbot-17-1127642.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Front Neurorobot","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:cb93b1d707744a61b40c035d8d8d19e5","is_oa":true,"landing_page_url":"https://doaj.org/article/cb93b1d707744a61b40c035d8d8d19e5","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Neurorobotics, Vol 17 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3389/fnbot.2023.1127642","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fnbot.2023.1127642","pdf_url":"https://www.frontiersin.org/articles/10.3389/fnbot.2023.1127642/pdf","source":{"id":"https://openalex.org/S115606517","display_name":"Frontiers in Neurorobotics","issn_l":"1662-5218","issn":["1662-5218"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Neurorobotics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.44999998807907104}],"awards":[{"id":"https://openalex.org/G6276684567","display_name":null,"funder_award_id":"TRR 169","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4382449266.pdf"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W1682403713","https://openalex.org/W2100675387","https://openalex.org/W2119885577","https://openalex.org/W2145339207","https://openalex.org/W2155007355","https://openalex.org/W2158782408","https://openalex.org/W2201581102","https://openalex.org/W2257979135","https://openalex.org/W2553098005","https://openalex.org/W2754791538","https://openalex.org/W2771461682","https://openalex.org/W2787938642","https://openalex.org/W2883265831","https://openalex.org/W2898417779","https://openalex.org/W2902456977","https://openalex.org/W2902907165","https://openalex.org/W2907537824","https://openalex.org/W2962887844","https://openalex.org/W2963390791","https://openalex.org/W2963864421","https://openalex.org/W2964048876","https://openalex.org/W2979216345","https://openalex.org/W2982316857","https://openalex.org/W2989847975","https://openalex.org/W3048263204","https://openalex.org/W3100226171","https://openalex.org/W3101480866","https://openalex.org/W3106070636","https://openalex.org/W3118210634","https://openalex.org/W3181648466","https://openalex.org/W4221164079","https://openalex.org/W4287324990","https://openalex.org/W4289753142","https://openalex.org/W4313116939","https://openalex.org/W4313563007","https://openalex.org/W4320858881","https://openalex.org/W4324028585","https://openalex.org/W6682849425","https://openalex.org/W6684921986","https://openalex.org/W6687681856","https://openalex.org/W6748839928","https://openalex.org/W6753199549","https://openalex.org/W6753505025","https://openalex.org/W6755950020","https://openalex.org/W6756754374","https://openalex.org/W6790689592","https://openalex.org/W6809990427","https://openalex.org/W6850099306"],"related_works":["https://openalex.org/W4213239787","https://openalex.org/W4377131110","https://openalex.org/W2045745654","https://openalex.org/W2114337652","https://openalex.org/W4388857216","https://openalex.org/W2046590706","https://openalex.org/W4390419005","https://openalex.org/W2949444602","https://openalex.org/W1587991081","https://openalex.org/W2386184744"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"agents":[4],"often":[5],"suffer":[6],"from":[7],"catastrophic":[8],"forgetting,":[9],"forgetting":[10],"previously":[11],"found":[12],"solutions":[13],"in":[14,132],"parts":[15],"of":[16,75,88,112],"the":[17,31,64,76,99,110],"input":[18],"space":[19],"when":[20],"training":[21,40],"new":[22,39],"data.":[23],"Replay":[24],"memories":[25],"are":[26],"a":[27,56,71,84],"common":[28],"solution":[29],"to":[30,97],"problem":[32],"by":[33],"decorrelating":[34],"and":[35,38,91,102],"shuffling":[36],"old":[37],"samples.":[41],"They":[42],"naively":[43],"store":[44],"state":[45,89],"transitions":[46,82],"as":[47],"they":[48],"arrive,":[49],"without":[50],"regard":[51],"for":[52,124],"redundancy.":[53],"We":[54],"introduce":[55],"novel":[57],"cognitive-inspired":[58],"replay":[59,122],"memory":[60,100,126],"approach":[61,79],"based":[62],"on":[63],"Grow-When-Required":[65],"(GWR)":[66],"self-organizing":[67],"network,":[68],"which":[69,108],"resembles":[70],"map-based":[72,120],"mental":[73],"model":[74],"world.":[77],"Our":[78],"organizes":[80],"stored":[81],"into":[83],"concise":[85],"environment-model-like":[86],"network":[87],"nodes":[90],"transition":[92],"edges,":[93],"merging":[94],"similar":[95],"samples":[96],"reduce":[98],"size":[101],"increase":[103],"pair-wise":[104],"distance":[105],"among":[106],"samples,":[107],"increases":[109],"relevancy":[111],"each":[113],"sample.":[114],"Overall,":[115],"our":[116],"study":[117],"shows":[118],"that":[119],"experience":[121],"allows":[123],"significant":[125],"reduction":[127],"with":[128],"only":[129],"small":[130],"decreases":[131],"performance.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}