{"id":"https://openalex.org/W2148349146","doi":null,"title":"Catastrophic Forgetting in Reinforcement-Learning Environments","display_name":"Catastrophic Forgetting in Reinforcement-Learning Environments","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2148349146","mag":"2148349146"},"language":"en","primary_location":{"id":"pmh:oai:alma.64OTAGO_INST:11396540960001891","doi":null,"is_oa":true,"landing_page_url":"https://ourarchive.otago.ac.nz/esploro/outputs/graduate/Catastrophic-Forgetting-in-Reinforcement-Learning-Environments/9926478601301891","pdf_url":"https://ourarchive.otago.ac.nz/view/delivery/64OTAGO_INST/12396540950001891/13397069110001891","source":{"id":"https://openalex.org/S4306402094","display_name":"Otago University Research Archive (University of Otago)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I80281795","host_organization_name":"University of Otago","host_organization_lineage":["https://openalex.org/I80281795"],"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":"Masters Thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ourarchive.otago.ac.nz/view/delivery/64OTAGO_INST/12396540950001891/13397069110001891","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082380091","display_name":"Andrew Cahill","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Andrew Cahill","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5082380091"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9922000169754028,"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":0.9922000169754028,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.006899999920278788,"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/T10320","display_name":"Neural Networks and Applications","score":0.0,"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/catastrophic-forgetting","display_name":"catastrophic forgetting","score":1.0},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.9459999799728394},{"id":"https://openalex.org/keywords/continual-learning","display_name":"continual learning","score":0.8240000009536743},{"id":"https://openalex.org/keywords/feedforward-neural-networks","display_name":"feedforward neural networks","score":0.906000018119812},{"id":"https://openalex.org/keywords/single-hidden-layer","display_name":"single hidden layer","score":0.8130000233650208},{"id":"https://openalex.org/keywords/function-approximation","display_name":"function approximation","score":0.8339999914169312}],"concepts":[{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.8364920616149902},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.599986732006073},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.46393683552742004},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.36781829595565796},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3483244776725769},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3348105549812317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2924812436103821},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2737114727497101},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.12538975477218628}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:alma.64OTAGO_INST:11396540960001891","doi":null,"is_oa":true,"landing_page_url":"https://ourarchive.otago.ac.nz/esploro/outputs/graduate/Catastrophic-Forgetting-in-Reinforcement-Learning-Environments/9926478601301891","pdf_url":"https://ourarchive.otago.ac.nz/view/delivery/64OTAGO_INST/12396540950001891/13397069110001891","source":{"id":"https://openalex.org/S4306402094","display_name":"Otago University Research Archive (University of Otago)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I80281795","host_organization_name":"University of Otago","host_organization_lineage":["https://openalex.org/I80281795"],"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":"Masters Thesis"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.854.1572","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.854.1572","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://ourarchive.otago.ac.nz/bitstream/handle/10523/1765/CahillAndrew2011MSc.pdf%3Bjsessionid%3DCB3D34744D47D5073FEB9C6430C3A3C5?sequence%3D3","raw_type":"text"},{"id":"pmh:oai:ourarchive.otago.ac.nz:10523/1765","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/10523/1765","pdf_url":null,"source":{"id":"https://openalex.org/S4306402094","display_name":"Otago University Research Archive (University of Otago)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I80281795","host_organization_name":"University of Otago","host_organization_lineage":["https://openalex.org/I80281795"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis or Dissertation"},{"id":"mag:2148349146","doi":null,"is_oa":false,"landing_page_url":"https://ourarchive.otago.ac.nz/bitstream/handle/10523/1765/cahillandrew2011msc.pdf?sequence=3","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:alma.64OTAGO_INST:11396540960001891","doi":null,"is_oa":true,"landing_page_url":"https://ourarchive.otago.ac.nz/esploro/outputs/graduate/Catastrophic-Forgetting-in-Reinforcement-Learning-Environments/9926478601301891","pdf_url":"https://ourarchive.otago.ac.nz/view/delivery/64OTAGO_INST/12396540950001891/13397069110001891","source":{"id":"https://openalex.org/S4306402094","display_name":"Otago University Research Archive (University of Otago)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I80281795","host_organization_name":"University of Otago","host_organization_lineage":["https://openalex.org/I80281795"],"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":"Masters Thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2148349146.pdf","grobid_xml":"https://content.openalex.org/works/W2148349146.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W36347840","https://openalex.org/W50296447","https://openalex.org/W1535804263","https://openalex.org/W1573706465","https://openalex.org/W1640646391","https://openalex.org/W1646707810","https://openalex.org/W1652505363","https://openalex.org/W1772845488","https://openalex.org/W1966295103","https://openalex.org/W2017338426","https://openalex.org/W2018124860","https://openalex.org/W2018383570","https://openalex.org/W2034920872","https://openalex.org/W2038994994","https://openalex.org/W2041367235","https://openalex.org/W2042524010","https://openalex.org/W2052089281","https://openalex.org/W2096712730","https://openalex.org/W2097082695","https://openalex.org/W2100602534","https://openalex.org/W2107726111","https://openalex.org/W2116522068","https://openalex.org/W2121796542","https://openalex.org/W2121863487","https://openalex.org/W2125074935","https://openalex.org/W2127104373","https://openalex.org/W2128687162","https://openalex.org/W2141559645","https://openalex.org/W2147786979","https://openalex.org/W2154987621","https://openalex.org/W2160644528","https://openalex.org/W2164724958","https://openalex.org/W2169969772","https://openalex.org/W2312756921","https://openalex.org/W2406065087","https://openalex.org/W2595408825","https://openalex.org/W2941735995","https://openalex.org/W3207342693"],"related_works":["https://openalex.org/W2888588005","https://openalex.org/W2902332709","https://openalex.org/W2778418400","https://openalex.org/W6922647895","https://openalex.org/W7078395502","https://openalex.org/W3084931530","https://openalex.org/W4416254794","https://openalex.org/W2902456977","https://openalex.org/W2107855852","https://openalex.org/W7058375971"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,10,29,90,136,233,249,258],"(RL)":[2],"problems":[3,234],"are":[4,15,100,118],"a":[5,79,217,253],"fundamental":[6,44],"part":[7],"of":[8,17,41,134,146,228,265],"machine":[9,28],"theory,":[11],"and":[12,21,111,138,193,221],"neural":[13,84,152,185,214],"networks":[14,85,153,186,215],"one":[16],"the":[18,39,106,144,224,263,285,290],"best":[19],"known":[20],"most":[22],"successful":[23,48],"general":[24],"tools":[25],"for":[26,73,154,245,277],"solving":[27,87],"problems.":[30],"Despite":[31],"this,":[32],"there":[33],"is":[34,75],"relatively":[35,225],"little":[36],"research":[37,113,141,162,203,279,292],"concerning":[38],"combination":[40],"these":[42],"two":[43],"ideas.":[45],"A":[46],"few":[47],"combined":[49],"frameworks":[50],"have":[51,63,125],"been":[52,159],"developed":[53],"(Lin,":[54],"1992),":[55],"but":[56,168],"researchers":[57,124],"often":[58],"find":[59],"that":[60,260],"their":[61],"implementations":[62],"unexpectedly":[64],"poor":[65],"performance":[66],"(Rivest":[67,175],"&":[68,176],"Precup,":[69,177],"2003).":[70],"One":[71],"explanation":[72],"this":[74,112,140,202,278],"Catastrophic":[76,128],"Forgetting":[77,129],"(CF),":[78],"problem":[80,107,145,264],"usually":[81],"faced":[82],"by":[83],"when":[86],"supervised":[88,109,135],"sequential":[89],"problems,":[91,167],"made":[92],"even":[93,194],"more":[94,195,246,287],"pressing":[95],"in":[96,108,119,130,148,165,208,280],"reinforcement":[97,232],"learning.":[98],"There":[99,157],"several":[101],"techniques":[102],"designed":[103],"to":[104,172,191,197,205,222,230,283,289],"alleviate":[105],"research,":[110],"investigates":[114],"how":[115],"useful":[116],"they":[117],"an":[120,241,281],"RL":[121,149,166,209,250,291],"context.":[122],"Previous":[123],"comprehensively":[126],"investigated":[127],"many":[131],"different":[132],"types":[133],"networks,":[137],"consequently":[139],"focuses":[142],"on":[143,163],"CF":[147,164,207,266],"agents":[150,210],"using":[151,211],"function":[155],"approximation.":[156],"has":[158,170],"some":[160],"previous":[161],"it":[169],"tended":[171],"be":[173,189],"incomplete":[174],"2003),":[178],"or":[179,252],"involve":[180],"complex":[181],"many-layered,":[182],"recurrent,":[183],"constructive":[184],"which":[187],"can":[188,261],"difficult":[190,196],"understand":[192],"implement":[198],"(Ring,":[199],"1994).":[200],"Instead,":[201],"aims":[204],"investigate":[206],"simple":[212,226],"feed-forward":[213],"with":[216,267],"single":[218],"hidden":[219],"layer,":[220],"apply":[223],"approach":[227],"pseudorehearsal":[229],"solve":[231],"effectively.":[235],"By":[236],"doing":[237],"so,":[238],"we":[239],"provide":[240],"easily":[242],"implemented":[243],"benchmark":[244],"sophisticated":[247],"continual":[248,257],"agents,":[251],"simple,":[254],"\u201egood":[255],"enough?":[256],"agent":[259],"avoid":[262],"reasonable":[268],"efficiency.":[269],"The":[270],"open":[271],"source":[272],"RL-Glue":[273],"framework":[274],"was":[275],"adopted":[276],"attempt":[282],"make":[284],"results":[286],"accessible":[288],"community":[293],"(Tanner,":[294],"2008).":[295]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}