{"id":"https://openalex.org/W2951348593","doi":"https://doi.org/10.48550/arxiv.1703.07075","title":"Pseudorehearsal in value function approximation","display_name":"Pseudorehearsal in value function approximation","publication_year":2017,"publication_date":"2017-03-21","ids":{"openalex":"https://openalex.org/W2951348593","doi":"https://doi.org/10.48550/arxiv.1703.07075","mag":"2951348593"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1703.07075","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.07075","pdf_url":"https://arxiv.org/pdf/1703.07075","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1703.07075","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047728360","display_name":"Vladimir Marochko","orcid":"https://orcid.org/0000-0001-9766-6420","observed_orcids":["https://orcid.org/0000-0001-9766-6420"]},"institutions":[{"id":"https://openalex.org/I4210116741","display_name":"Innopolis University","ror":"https://ror.org/02b7jh107","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210116741"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Marochko, Vladimir","raw_affiliation_strings":["Innopolis University Universitetskaya str. 1 , 420500 Innopolis , Russia","Innopolis University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innopolis University Universitetskaya str. 1 , 420500 Innopolis , Russia","institution_ids":["https://openalex.org/I4210116741"]},{"raw_affiliation_string":"Innopolis University","institution_ids":["https://openalex.org/I4210116741"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010557969","display_name":"Leonard Johard","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210116741","display_name":"Innopolis University","ror":"https://ror.org/02b7jh107","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210116741"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Johard, Leonard","raw_affiliation_strings":["Innopolis University Universitetskaya str. 1 , 420500 Innopolis , Russia","Innopolis University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innopolis University Universitetskaya str. 1 , 420500 Innopolis , Russia","institution_ids":["https://openalex.org/I4210116741"]},{"raw_affiliation_string":"Innopolis University","institution_ids":["https://openalex.org/I4210116741"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075175655","display_name":"Manuel Mazzara","orcid":"https://orcid.org/0000-0002-3860-4948","observed_orcids":["https://orcid.org/0000-0002-3860-4948"]},"institutions":[{"id":"https://openalex.org/I4210116741","display_name":"Innopolis University","ror":"https://ror.org/02b7jh107","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210116741"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Mazzara, Manuel","raw_affiliation_strings":["Innopolis University Universitetskaya str. 1 , 420500 Innopolis , Russia","Innopolis University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innopolis University Universitetskaya str. 1 , 420500 Innopolis , Russia","institution_ids":["https://openalex.org/I4210116741"]},{"raw_affiliation_string":"Innopolis University","institution_ids":["https://openalex.org/I4210116741"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210116741"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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":0.9994999766349792,"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":0.9994999766349792,"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":0.00039999998989515007,"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/T10906","display_name":"AI-based Problem Solving and Planning","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":0.9879999756813049},{"id":"https://openalex.org/keywords/value-function-approximation","display_name":"value function approximation","score":0.8550000190734863},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.9879999756813049},{"id":"https://openalex.org/keywords/function-approximation","display_name":"function approximation","score":0.7070000171661377},{"id":"https://openalex.org/keywords/non-stationary-data-distributions","display_name":"non-stationary data distributions","score":0.871999979019165}],"concepts":[{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.9458010196685791},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.8409056067466736},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6686079502105713},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6011731028556824},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5881510376930237},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.5694383382797241},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5634119510650635},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5322195291519165},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5320367217063904},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4340149760246277},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3889525234699249},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.30043283104896545},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23869279026985168},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22399911284446716},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10471725463867188},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.09078896045684814},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.0857560932636261},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07175591588020325},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1703.07075","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.07075","pdf_url":"https://arxiv.org/pdf/1703.07075","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"mag:2951348593","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1703.07075","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1703.07075","doi":"https://doi.org/10.48550/arxiv.1703.07075","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1703.07075","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1703.07075","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.07075","pdf_url":"https://arxiv.org/pdf/1703.07075","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2951348593.pdf","grobid_xml":"https://content.openalex.org/works/W2951348593.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1525859397","https://openalex.org/W1595483645","https://openalex.org/W1757796397","https://openalex.org/W1967094725","https://openalex.org/W1982262386","https://openalex.org/W2036963181","https://openalex.org/W2047057213","https://openalex.org/W2052089281","https://openalex.org/W2073256825","https://openalex.org/W2081117954","https://openalex.org/W2091894052","https://openalex.org/W2097082695","https://openalex.org/W2100677568","https://openalex.org/W2115599650","https://openalex.org/W2116522068","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2271272582","https://openalex.org/W2514480443"],"related_works":["https://openalex.org/W6922647895","https://openalex.org/W2778418400","https://openalex.org/W7099815579","https://openalex.org/W51508254","https://openalex.org/W7098200929","https://openalex.org/W7095367389","https://openalex.org/W2230868825","https://openalex.org/W2496512422","https://openalex.org/W7098038548","https://openalex.org/W29557895"],"abstract_inverted_index":{"Catastrophic":[0],"forgetting":[1],"is":[2,13],"of":[3,53],"special":[4],"importance":[5],"in":[6,30,45],"reinforcement":[7],"learning,":[8],"as":[9],"the":[10,54],"data":[11],"distribution":[12],"generally":[14],"non-stationary":[15],"over":[16],"time.":[17],"We":[18,35],"study":[19],"and":[20],"compare":[21],"several":[22],"pseudorehearsal":[23,39],"approaches":[24],"for":[25],"Q-learning":[26],"with":[27],"function":[28],"approximation":[29],"a":[31],"pole":[32],"balancing":[33],"task.":[34],"have":[36],"found":[37],"that":[38],"seems":[40],"to":[41],"assist":[42],"learning":[43],"even":[44],"such":[46],"very":[47],"simple":[48],"problems,":[49],"given":[50],"proper":[51],"initialization":[52],"rehearsal":[55],"parameters.":[56]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-06-27T00:00:00"}