{"id":"https://openalex.org/W4403278684","doi":"https://doi.org/10.1109/is61756.2024.10705256","title":"Continual Reinforcement Learning Without Replay Buffers","display_name":"Continual Reinforcement Learning Without Replay Buffers","publication_year":2024,"publication_date":"2024-08-29","ids":{"openalex":"https://openalex.org/W4403278684","doi":"https://doi.org/10.1109/is61756.2024.10705256"},"language":"en","primary_location":{"id":"doi:10.1109/is61756.2024.10705256","is_oa":false,"landing_page_url":"https://doi.org/10.1109/is61756.2024.10705256","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 12th International Conference on Intelligent Systems (IS)","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/A5091391308","display_name":"Alexander Krawczyk","orcid":null},"institutions":[{"id":"https://openalex.org/I201850948","display_name":"Fulda University of Applied Sciences","ror":"https://ror.org/041bz9r75","country_code":"DE","type":"education","lineage":["https://openalex.org/I201850948"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Alexander Krawczyk","raw_affiliation_strings":["University of Applied Sciences Fulda,Applied Computer Science Department,Fulda,Germany,36037"],"affiliations":[{"raw_affiliation_string":"University of Applied Sciences Fulda,Applied Computer Science Department,Fulda,Germany,36037","institution_ids":["https://openalex.org/I201850948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078051370","display_name":"Benedikt Bagus","orcid":null},"institutions":[{"id":"https://openalex.org/I201850948","display_name":"Fulda University of Applied Sciences","ror":"https://ror.org/041bz9r75","country_code":"DE","type":"education","lineage":["https://openalex.org/I201850948"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Benedikt Bagus","raw_affiliation_strings":["University of Applied Sciences Fulda,Applied Computer Science Department,Fulda,Germany,36037"],"affiliations":[{"raw_affiliation_string":"University of Applied Sciences Fulda,Applied Computer Science Department,Fulda,Germany,36037","institution_ids":["https://openalex.org/I201850948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108184212","display_name":"Yannick Denker","orcid":null},"institutions":[{"id":"https://openalex.org/I201850948","display_name":"Fulda University of Applied Sciences","ror":"https://ror.org/041bz9r75","country_code":"DE","type":"education","lineage":["https://openalex.org/I201850948"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yannick Denker","raw_affiliation_strings":["University of Applied Sciences Fulda,Applied Computer Science Department,Fulda,Germany,36037"],"affiliations":[{"raw_affiliation_string":"University of Applied Sciences Fulda,Applied Computer Science Department,Fulda,Germany,36037","institution_ids":["https://openalex.org/I201850948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030810660","display_name":"Alexander Gepperth","orcid":"https://orcid.org/0000-0003-2216-7808"},"institutions":[{"id":"https://openalex.org/I201850948","display_name":"Fulda University of Applied Sciences","ror":"https://ror.org/041bz9r75","country_code":"DE","type":"education","lineage":["https://openalex.org/I201850948"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander Gepperth","raw_affiliation_strings":["University of Applied Sciences Fulda,Applied Computer Science Department,Fulda,Germany,36037"],"affiliations":[{"raw_affiliation_string":"University of Applied Sciences Fulda,Applied Computer Science Department,Fulda,Germany,36037","institution_ids":["https://openalex.org/I201850948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5091391308"],"corresponding_institution_ids":["https://openalex.org/I201850948"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15455094,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9296000003814697,"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":0.9296000003814697,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8394697904586792},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7369215488433838},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4427739083766937},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28320181369781494},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09612566232681274}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8394697904586792},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7369215488433838},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4427739083766937},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28320181369781494},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09612566232681274},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/is61756.2024.10705256","is_oa":false,"landing_page_url":"https://doi.org/10.1109/is61756.2024.10705256","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 12th International Conference on Intelligent Systems (IS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1682403713","https://openalex.org/W2036963181","https://openalex.org/W2119885577","https://openalex.org/W2141559645","https://openalex.org/W2560647685","https://openalex.org/W2746553466","https://openalex.org/W2786446225","https://openalex.org/W2787666871","https://openalex.org/W2902332709","https://openalex.org/W2996514457","https://openalex.org/W3027406032","https://openalex.org/W3030364939","https://openalex.org/W3048941751","https://openalex.org/W3117215073","https://openalex.org/W3163939464","https://openalex.org/W3165727671","https://openalex.org/W3194195161","https://openalex.org/W3198317271","https://openalex.org/W3204102604","https://openalex.org/W4214717370","https://openalex.org/W4249244053","https://openalex.org/W4312370949","https://openalex.org/W4312473854","https://openalex.org/W4386736782","https://openalex.org/W4400680576","https://openalex.org/W4402351637","https://openalex.org/W4402917191","https://openalex.org/W6685444567","https://openalex.org/W6741087337","https://openalex.org/W6756754374","https://openalex.org/W6803204313","https://openalex.org/W6804044274","https://openalex.org/W6838929685","https://openalex.org/W6859263116"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588"],"abstract_inverted_index":{"We":[0],"introduce":[1,76,130],"a":[2,49,116],"novel":[3,158],"technique":[4],"to":[5,21,26,57,82,148,156],"address":[6],"continual":[7,124],"reinforcement":[8,12],"learning":[9,13,125],"(CRL),":[10],"i.e.,":[11],"(RL)":[14],"in":[15,69],"non-stationary":[16],"environments.":[17],"This":[18],"requires":[19],"agents":[20],"rapidly":[22],"update":[23],"their":[24],"policies":[25,152],"new":[27,63],"statistics":[28,64],"while":[29,153],"avoiding":[30],"the":[31,70],"catastrophic":[32],"forgetting":[33],"(CF)":[34],"of":[35,60],"previous":[36],"policies.":[37],"In":[38,72],"RL,":[39],"CF":[40],"is":[41],"commonly":[42],"circumvented":[43],"by":[44,141],"experience":[45],"replay":[46,114,120],"(ER)":[47],"from":[48],"large":[50],"buffer.":[51,71],"As":[52],"we":[53,129],"show,":[54],"this":[55],"leads":[56],"slow":[58],"updating":[59],"policies,":[61],"since":[62],"must":[65],"be":[66],"sufficiently":[67],"represented":[68],"addition,":[73],"non-stationarities":[74],"can":[75],"contradictions":[77],"that":[78],"an":[79],"agent":[80],"needs":[81],"adapt":[83],"to.":[84],"Our":[85],"approach,":[86],"unlike":[87],"traditional":[88],"methods":[89],"such":[90],"as":[91],"deep":[92],"Q-networks":[93],"(DQNs)":[94],"with":[95],"ER,":[96],"enables":[97],"fast":[98],"reaction":[99],"times":[100],"under":[101],"minimal":[102],"memory":[103],"requirements,":[104],"making":[105],"it":[106],"suitable":[107],"for":[108,123],"real-world":[109],"applications.":[110],"It":[111],"generalizes":[112],"adiabatic":[113],"(AR),":[115],"recently":[117],"introduced":[118],"generative":[119],"(GR)":[121],"method":[122],"(CL).":[126],"For":[127],"evaluation,":[128],"two":[131],"robotic":[132],"simulation-based":[133],"CRL":[134],"benchmarks":[135],"which":[136],"are":[137],"partitioned":[138],"into":[139],"tasks":[140],"environment":[142],"shifts,":[143],"showcasing":[144],"our":[145],"approach's":[146],"ability":[147],"retain":[149],"previously":[150],"acquired":[151],"being":[154],"able":[155],"learn":[157],"skills.":[159]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}