{"id":"https://openalex.org/W3131024358","doi":null,"title":"Testbeds for Reinforcement Learning.","display_name":"Testbeds for Reinforcement Learning.","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3131024358","mag":"3131024358"},"language":"en","primary_location":{"id":"mag:3131024358","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2011.04590","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":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/abs/2011.04590","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083856371","display_name":"Banafsheh Rafiee","orcid":"https://orcid.org/0000-0003-4641-7349","observed_orcids":["https://orcid.org/0000-0003-4641-7349"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Banafsheh Rafiee","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-4641-7349","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5083856371"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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":0.9721999764442444,"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":0.9721999764442444,"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":0.008100000210106373,"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":0.007000000216066837,"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/classical-conditioning","display_name":"classical conditioning","score":0.7590000033378601},{"id":"https://openalex.org/keywords/temporal-association","display_name":"temporal association","score":0.6700000166893005},{"id":"https://openalex.org/keywords/recurrent-neural-networks","display_name":"recurrent neural networks","score":0.7329999804496765},{"id":"https://openalex.org/keywords/online-prediction","display_name":"online prediction","score":0.765999972820282},{"id":"https://openalex.org/keywords/continual-learning","display_name":"continual learning","score":0.7229999899864197},{"id":"https://openalex.org/keywords/representation-learning","display_name":"representation learning","score":0.527999997138977},{"id":"https://openalex.org/keywords/multi-step-forecasting","display_name":"multi-step forecasting","score":0.6110000014305115}],"concepts":[{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.7583802938461304},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7418649196624756},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7371796369552612},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7061011791229248},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6821417212486267},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.6351506114006042},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5772325992584229},{"id":"https://openalex.org/C2775941552","wikidata":"https://www.wikidata.org/wiki/Q25212305","display_name":"Isolation (microbiology)","level":2,"score":0.5312399864196777},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5190394520759583},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.49137797951698303},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4883806109428406},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08232620358467102},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C89423630","wikidata":"https://www.wikidata.org/wiki/Q7193","display_name":"Microbiology","level":1,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3131024358","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2011.04590","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":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3131024358","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2011.04590","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":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1924770834","https://openalex.org/W2011868317","https://openalex.org/W2025205736","https://openalex.org/W2052552354","https://openalex.org/W2064675550","https://openalex.org/W2092790999","https://openalex.org/W2100677568","https://openalex.org/W2109910161","https://openalex.org/W2110485445","https://openalex.org/W2121863487","https://openalex.org/W2150468603","https://openalex.org/W2151742051","https://openalex.org/W2754879180","https://openalex.org/W2766736793","https://openalex.org/W2786036274","https://openalex.org/W2794752562","https://openalex.org/W2970567787"],"related_works":["https://openalex.org/W3105973574","https://openalex.org/W3176334129","https://openalex.org/W6978194966","https://openalex.org/W6921453256","https://openalex.org/W2907495747","https://openalex.org/W1904406446","https://openalex.org/W2149977209","https://openalex.org/W577502697","https://openalex.org/W6921767107","https://openalex.org/W2911817271"],"abstract_inverted_index":{"Experiments":[0],"in":[1,80,128,138],"classical":[2],"conditioning":[3],"show":[4],"that":[5,18,35,101],"animals":[6,102],"such":[7],"as":[8],"rabbits,":[9],"pigeons,":[10],"and":[11,47,105,126],"dogs":[12],"can":[13,43],"make":[14],"long":[15],"temporal":[16,49],"associations":[17],"enable":[19],"multi-step":[20],"prediction.":[21],"To":[22,77],"replicate":[23],"this":[24,75],"remarkable":[25],"ability,":[26],"an":[27,31],"agent":[28],"must":[29],"construct":[30,45],"internal":[32],"state":[33,46],"representation":[34,147],"summarizes":[36],"its":[37],"interaction":[38],"history.":[39],"Recurrent":[40],"neural":[41],"networks":[42],"automatically":[44],"learn":[48],"associations.":[50],"But":[51],"the":[52,72,98,107,114,129],"current":[53,108],"training":[54],"methods":[55],"are":[56,117,120],"prohibitively":[57],"expensive":[58],"for":[59],"online":[60,81,146],"prediction":[61,88],"--":[62,69],"continual":[63],"learning":[64,99,110,148],"on":[65],"every":[66],"time":[67],"step":[68],"which":[70],"is":[71],"focus":[73],"of":[74],"paper.":[76],"facilitate":[78],"research":[79],"prediction,":[82],"we":[83],"present":[84],"three":[85],"new":[86],"diagnostic":[87],"problems":[89,96,116],"inspired":[90],"by":[91],"classical-conditioning":[92],"experiments.":[93],"The":[94],"proposed":[95,115],"test":[97],"capabilities":[100],"readily":[103],"exhibit":[104],"highlight":[106],"recurrent":[109],"methods'":[111],"limitations.":[112],"While":[113],"nontrivial,":[118],"they":[119],"still":[121],"amenable":[122],"to":[123,135],"extensive":[124],"testing":[125],"analysis":[127],"small-compute":[130],"regime,":[131],"thereby":[132],"enabling":[133],"researchers":[134],"study":[136],"issues":[137],"isolation":[139],"carefully,":[140],"ultimately":[141],"accelerating":[142],"progress":[143],"towards":[144],"scalable":[145],"methods.":[149]},"counts_by_year":[],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2021-03-01T00:00:00"}