{"id":"https://openalex.org/W2902033370","doi":null,"title":"Prioritizing Starting States for Reinforcement Learning.","display_name":"Prioritizing Starting States for Reinforcement Learning.","publication_year":2018,"publication_date":"2018-11-27","ids":{"openalex":"https://openalex.org/W2902033370","mag":"2902033370"},"language":"en","primary_location":{"id":"mag:2902033370","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1811.11298v2","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},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1811.11298v2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081617594","display_name":"Arash Tavakoli","orcid":"https://orcid.org/0000-0001-8481-3284","observed_orcids":["https://orcid.org/0000-0001-8481-3284"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arash Tavakoli","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-8481-3284","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009542795","display_name":"Vitaly Levdik","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vitaly Levdik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079926596","display_name":"Riashat Islam","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Riashat Islam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5036281885","display_name":"Petar S. Kormushev","orcid":"https://orcid.org/0000-0002-6677-3044","observed_orcids":["https://orcid.org/0000-0002-6677-3044"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Petar Kormushev","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-6677-3044","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"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":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","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/experience-memory","display_name":"experience memory","score":0.7369999885559082},{"id":"https://openalex.org/keywords/exploration","display_name":"exploration","score":0.6660000085830688},{"id":"https://openalex.org/keywords/off-policy-learning","display_name":"off-policy learning","score":0.8209999799728394},{"id":"https://openalex.org/keywords/on-policy-learning","display_name":"on-policy learning","score":0.9900000095367432},{"id":"https://openalex.org/keywords/sparse-rewards","display_name":"sparse rewards","score":0.5740000009536743},{"id":"https://openalex.org/keywords/replay-buffer","display_name":"replay buffer","score":0.3930000066757202},{"id":"https://openalex.org/keywords/state-space-coverage","display_name":"state space coverage","score":0.7039999961853027},{"id":"https://openalex.org/keywords/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.6940000057220459}],"concepts":[{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.9165405035018921},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8531703948974609},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.693832278251648},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6471007466316223},{"id":"https://openalex.org/C2777615720","wikidata":"https://www.wikidata.org/wiki/Q11888847","display_name":"Prioritization","level":2,"score":0.5533909797668457},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5122701525688171},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5007574558258057},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.43860650062561035},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4209868311882019},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.27129900455474854},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.16350141167640686},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.12740060687065125},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08968088030815125},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08617499470710754},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":2,"locations":[{"id":"mag:2902033370","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1811.11298v2","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":"pmh:oai:spiral.imperial.ac.uk:10044/1/71857","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/10044/1/71857","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Working Paper"}],"best_oa_location":{"id":"mag:2902033370","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1811.11298v2","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},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1512919909","https://openalex.org/W1575592356","https://openalex.org/W1602154927","https://openalex.org/W1777239053","https://openalex.org/W1927790226","https://openalex.org/W2034806191","https://openalex.org/W2052117683","https://openalex.org/W2073384958","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2158782408","https://openalex.org/W2173248099","https://openalex.org/W2201581102","https://openalex.org/W2312609093","https://openalex.org/W2419612459","https://openalex.org/W2551887912","https://openalex.org/W2610395436","https://openalex.org/W2614839826","https://openalex.org/W2623491082","https://openalex.org/W2736601468","https://openalex.org/W2737215407","https://openalex.org/W2766447205","https://openalex.org/W2785533664","https://openalex.org/W2789008106","https://openalex.org/W2804380964","https://openalex.org/W2904157920","https://openalex.org/W2914261249","https://openalex.org/W2949608212","https://openalex.org/W2962749646","https://openalex.org/W2962832483","https://openalex.org/W2963184939","https://openalex.org/W2963193690","https://openalex.org/W2964986650","https://openalex.org/W3039845099","https://openalex.org/W6998967213"],"related_works":["https://openalex.org/W6929140826","https://openalex.org/W2201581102","https://openalex.org/W3051139937","https://openalex.org/W3207494445","https://openalex.org/W2789097347","https://openalex.org/W4411551944","https://openalex.org/W4415347882","https://openalex.org/W7133205423","https://openalex.org/W3211545083","https://openalex.org/W3041067791"],"abstract_inverted_index":{"Online,":[0],"off-policy":[1,191],"reinforcement":[2,195],"learning":[3,187,196],"algorithms":[4],"are":[5],"able":[6],"to":[7,12,25,59,90,97,110,115,146,155],"use":[8],"an":[9,56],"experience":[10,57],"memory":[11,58],"remember":[13],"and":[14,36,122,192],"replay":[15],"past":[16,99,117,149],"experiences.":[17,44],"In":[18,45],"prior":[19],"work,":[20,47],"this":[21,46,103],"approach":[22,185],"was":[23],"used":[24],"stabilize":[26],"training":[27],"by":[28,62,105],"breaking":[29],"the":[30,34,38,64,69,74,88,92,108,128],"temporal":[31],"correlations":[32],"of":[33,41,127,138],"updates":[35],"avoiding":[37],"rapid":[39],"forgetting":[40],"possibly":[42],"rare":[43],"we":[48,101,151,167],"propose":[49],"a":[50,78,134,142],"conceptually":[51],"simple":[52],"framework":[53],"that":[54,80,169,183],"uses":[55],"help":[60,158],"exploration":[61,159],"prioritizing":[63],"starting":[65,132],"states":[66,95,113],"from":[67,133],"which":[68],"agent":[70,93,109],"starts":[71],"acting":[72],"in":[73,77,94,112,160,202],"environment,":[75],"importantly,":[76],"fashion":[79],"is":[81],"also":[82],"compatible":[83],"with":[84,198],"on-policy":[85,193],"algorithms.":[86],"Given":[87],"capacity":[89],"restart":[91,111],"corresponding":[96],"its":[98],"observations,":[100],"achieve":[102],"objective":[104],"(i)":[106,154],"enabling":[107],"belonging":[114],"significant":[116,148],"experiences":[118],"(e.g.,":[119,163],"nearby":[120],"goals),":[121],"(ii)":[123,171],"promoting":[124],"faster":[125],"coverage":[126],"state":[129],"space":[130],"through":[131],"more":[135,156],"diverse":[136],"set":[137],"states.":[139],"While,":[140],"using":[141],"good":[143],"priority":[144],"measure":[145],"identify":[147],"transitions,":[150],"expect":[152],"case":[153,170],"considerably":[157],"certain":[161],"domains":[162],"sparse":[164,204],"reward":[165,205],"tasks),":[166],"hypothesize":[168],"will":[172],"generally":[173],"be":[174],"beneficial,":[175],"even":[176],"without":[177],"any":[178],"prioritization.":[179],"We":[180],"show":[181],"empirically":[182],"our":[184],"improves":[186],"performance":[188],"for":[189],"both":[190],"deep":[194],"methods,":[197],"most":[199],"notable":[200],"gains":[201],"highly":[203],"tasks.":[206]},"counts_by_year":[{"year":2020,"cited_by_count":3}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2018-12-11T00:00:00"}