{"id":"https://openalex.org/W3131923042","doi":null,"title":"Beyond Prioritized Replay: Sampling States in Model-Based Reinforcement Learning via Simulated Priorities","display_name":"Beyond Prioritized Replay: Sampling States in Model-Based Reinforcement Learning via Simulated Priorities","publication_year":2020,"publication_date":"2020-07-19","ids":{"openalex":"https://openalex.org/W3131923042","mag":"3131923042"},"language":"en","primary_location":{"id":"mag:3131923042","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2007.09569","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/abs/2007.09569","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014823249","display_name":"Jincheng Mei","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jincheng Mei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051536192","display_name":"Yangchen Pan","orcid":"https://orcid.org/0009-0000-8297-9045","observed_orcids":["https://orcid.org/0009-0000-8297-9045"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yangchen Pan","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0000-8297-9045","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109495187","display_name":"Amir\u2010massoud Farahmand","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amir\u2010massoud Farahmand","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050876115","display_name":"Hengshuai Yao","orcid":"https://orcid.org/0000-0003-1258-1845","observed_orcids":["https://orcid.org/0000-0003-1258-1845"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hengshuai Yao","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-1258-1845","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101613484","display_name":"Martha White","orcid":"https://orcid.org/0000-0002-5356-2950","observed_orcids":["https://orcid.org/0000-0002-5356-2950"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martha White","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-5356-2950","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":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":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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11195","display_name":"Simulation Techniques and Applications","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/prioritized-experience-replay","display_name":"prioritized experience replay","score":0.9909999966621399},{"id":"https://openalex.org/keywords/model-based-reinforcement-learning","display_name":"model-based reinforcement learning","score":0.8339999914169312},{"id":"https://openalex.org/keywords/state-sampling","display_name":"state sampling","score":0.7179999947547913},{"id":"https://openalex.org/keywords/stochastic-gradient-langevin-dynamics","display_name":"stochastic gradient Langevin dynamics","score":0.8330000042915344},{"id":"https://openalex.org/keywords/convergence-rate","display_name":"convergence rate","score":0.6729999780654907},{"id":"https://openalex.org/keywords/autonomous-driving","display_name":"autonomous driving","score":0.5370000004768372}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7521066665649414},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6890418529510498},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6155408620834351},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5244189500808716},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.45709505677223206},{"id":"https://openalex.org/C2776639384","wikidata":"https://www.wikidata.org/wiki/Q840396","display_name":"Ideal (ethics)","level":2,"score":0.42995309829711914},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4277370572090149},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38468503952026367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3790176212787628},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1925276219844818},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.1611516773700714},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14867207407951355},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3131923042","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2007.09569","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}],"best_oa_location":{"id":"mag:3131923042","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2007.09569","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":62,"referenced_works":["https://openalex.org/W1491843047","https://openalex.org/W1533861849","https://openalex.org/W1758031947","https://openalex.org/W1870822514","https://openalex.org/W1954227087","https://openalex.org/W1982262386","https://openalex.org/W1983452151","https://openalex.org/W2006398000","https://openalex.org/W2024390895","https://openalex.org/W2041898787","https://openalex.org/W2046033161","https://openalex.org/W2048226872","https://openalex.org/W2073384958","https://openalex.org/W2107726111","https://openalex.org/W2114384389","https://openalex.org/W2121863487","https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2159136633","https://openalex.org/W2165150801","https://openalex.org/W2167433878","https://openalex.org/W2173248099","https://openalex.org/W2201581102","https://openalex.org/W2290354866","https://openalex.org/W2590516361","https://openalex.org/W2626747984","https://openalex.org/W2733961795","https://openalex.org/W2772721022","https://openalex.org/W2786928559","https://openalex.org/W2786969620","https://openalex.org/W2796054047","https://openalex.org/W2883207481","https://openalex.org/W2890208753","https://openalex.org/W2890960027","https://openalex.org/W2892979040","https://openalex.org/W2900152462","https://openalex.org/W2901850563","https://openalex.org/W2902098903","https://openalex.org/W2927603314","https://openalex.org/W2962986780","https://openalex.org/W2963079702","https://openalex.org/W2963207607","https://openalex.org/W2963582482","https://openalex.org/W2964121744","https://openalex.org/W2964291307","https://openalex.org/W2965870268","https://openalex.org/W2966234803","https://openalex.org/W2970065541","https://openalex.org/W2970202659","https://openalex.org/W2970277495","https://openalex.org/W2970998096","https://openalex.org/W2989847975","https://openalex.org/W2996283994","https://openalex.org/W2998202787","https://openalex.org/W3034971196","https://openalex.org/W3041568888","https://openalex.org/W3101275829","https://openalex.org/W3107736070","https://openalex.org/W3123212791","https://openalex.org/W3126457809","https://openalex.org/W6978325088"],"related_works":["https://openalex.org/W4287713698","https://openalex.org/W3043761458","https://openalex.org/W7133225271","https://openalex.org/W3161370204","https://openalex.org/W3203449083","https://openalex.org/W3211545083","https://openalex.org/W2042296018","https://openalex.org/W4389317899","https://openalex.org/W7223113070","https://openalex.org/W6967248187"],"abstract_inverted_index":{"The":[0],"prioritized":[1,34,48,91,132],"Experience":[2],"Replay":[3],"(ER)":[4],"method":[5,50,123,170],"has":[6],"attracted":[7],"great":[8],"attention;":[9],"however,":[10],"there":[11],"is":[12],"little":[13],"theoretical":[14,65],"understanding":[15],"about":[16],"why":[17,68],"it":[18,69],"can":[19],"help":[20],"and":[21,55,97,154,163],"its":[22],"limitations.":[23,147],"In":[24,36],"this":[25],"work,":[26],"we":[27,41,83,109],"take":[28],"a":[29,37],"deep":[30],"look":[31],"at":[32],"the":[33,43,46,81,90,102,107,137,145,165],"ER.":[35],"supervised":[38],"learning":[39],"setting,":[40],"show":[42,120,159],"equivalence":[44],"between":[45],"error-based":[47],"sampling":[49,57,75,117,133],"for":[51,58],"mean":[52],"squared":[53],"error":[54],"uniform":[56,74],"cubic":[59],"power":[60],"loss.":[61],"We":[62,119,148],"then":[63],"provide":[64,125],"insight":[66],"into":[67],"improves":[70],"convergence":[71],"rate":[72],"upon":[73],"during":[76],"early":[77],"learning.":[78],"Based":[79],"on":[80,151],"insight,":[82],"further":[84],"point":[85],"out":[86],"two":[87,146],"limitations":[88],"of":[89,101,168],"ER":[92],"method:":[93],"1)":[94],"outdated":[95],"priorities":[96],"2)":[98],"insufficient":[99],"coverage":[100],"sample":[103],"space.":[104],"To":[105],"mitigate":[106],"limitations,":[108],"propose":[110],"our":[111,122,160,169],"model-based":[112],"stochastic":[113],"gradient":[114],"Langevin":[115],"dynamics":[116],"method.":[118],"that":[121],"does":[124,141],"states":[126],"distributed":[127],"close":[128],"to":[129,158],"an":[130,172],"ideal":[131],"distribution":[134],"estimated":[135],"by":[136],"brute-force":[138],"method,":[139],"which":[140],"not":[142],"suffer":[143],"from":[144],"conduct":[149],"experiments":[150],"both":[152],"discrete":[153],"continuous":[155],"control":[156],"problems":[157],"approach's":[161],"efficacy":[162],"examine":[164],"practical":[166],"implication":[167],"in":[171],"autonomous":[173],"driving":[174],"application.":[175]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2021-03-01T00:00:00"}