{"id":"https://openalex.org/W2963582482","doi":"https://doi.org/10.24963/ijcai.2018/666","title":"Organizing Experience: a Deeper Look at Replay Mechanisms for Sample-Based Planning in Continuous State Domains","display_name":"Organizing Experience: a Deeper Look at Replay Mechanisms for Sample-Based Planning in Continuous State Domains","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2963582482","doi":"https://doi.org/10.24963/ijcai.2018/666","mag":"2963582482"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2018/666","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/666","pdf_url":"https://www.ijcai.org/proceedings/2018/0666.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2018/0666.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051536192","display_name":"Yangchen Pan","orcid":"https://orcid.org/0009-0000-8297-9045"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yangchen Pan","raw_affiliation_strings":["University of Alberta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004839726","display_name":"Muhammad Zaigham Zaheer","orcid":"https://orcid.org/0000-0001-8272-1351"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Muhammad Zaheer","raw_affiliation_strings":["University of Alberta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101954122","display_name":"Adam White","orcid":"https://orcid.org/0000-0002-6449-0622"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["CA","GB"],"is_corresponding":false,"raw_author_name":"Adam White","raw_affiliation_strings":["Deepmind","University of Alberta","DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deepmind","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103118703","display_name":"Andrew Patterson","orcid":"https://orcid.org/0000-0003-2461-3103"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Andrew Patterson","raw_affiliation_strings":["University of Alberta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101613484","display_name":"Martha White","orcid":"https://orcid.org/0000-0002-5356-2950"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Martha White","raw_affiliation_strings":["University of Alberta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.0549,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.95129084,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4794","last_page":"4800"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9937999844551086,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9937999844551086,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9936000108718872,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9908999800682068,"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/computer-science","display_name":"Computer science","score":0.8300982713699341},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6929634809494019},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.6783146858215332},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4960063397884369},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.44337987899780273},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4324081242084503},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4254203736782074},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3940606713294983},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1515125334262848}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8300982713699341},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6929634809494019},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.6783146858215332},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4960063397884369},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.44337987899780273},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4324081242084503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4254203736782074},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3940606713294983},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1515125334262848},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2018/666","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/666","pdf_url":"https://www.ijcai.org/proceedings/2018/0666.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2018/666","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/666","pdf_url":"https://www.ijcai.org/proceedings/2018/0666.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963582482.pdf","grobid_xml":"https://content.openalex.org/works/W2963582482.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W223326216","https://openalex.org/W314779054","https://openalex.org/W1002758560","https://openalex.org/W1682403713","https://openalex.org/W1757660428","https://openalex.org/W1758031947","https://openalex.org/W1870822514","https://openalex.org/W1985054922","https://openalex.org/W1988526405","https://openalex.org/W2060277733","https://openalex.org/W2097575529","https://openalex.org/W2114384389","https://openalex.org/W2130105540","https://openalex.org/W2140135625","https://openalex.org/W2188365844","https://openalex.org/W2201581102","https://openalex.org/W2287437177","https://openalex.org/W2561828331","https://openalex.org/W2568999269","https://openalex.org/W2572640103","https://openalex.org/W2740764198","https://openalex.org/W2949361666","https://openalex.org/W2950471160","https://openalex.org/W2963394426","https://openalex.org/W2964067969","https://openalex.org/W4214717370","https://openalex.org/W4229706854","https://openalex.org/W4245108548","https://openalex.org/W4254755460","https://openalex.org/W4298028931","https://openalex.org/W4299570260","https://openalex.org/W4320013936"],"related_works":["https://openalex.org/W4236696095","https://openalex.org/W3143779693","https://openalex.org/W2626808643","https://openalex.org/W2004064826","https://openalex.org/W3103727510","https://openalex.org/W97045569","https://openalex.org/W1527069879","https://openalex.org/W2946179579","https://openalex.org/W2348021072","https://openalex.org/W1871370349"],"abstract_inverted_index":{"Model-based":[0],"strategies":[1],"for":[2,114],"control":[3],"are":[4],"critical":[5],"to":[6,26,49,96,107,118,153,183],"obtain":[7],"sample":[8,85,119,154],"efficient":[9],"learning.":[10],"Dyna":[11],"is":[12,48,111],"a":[13,68,87,103,108,133,139],"planning":[14,33,81],"paradigm":[15],"that":[16,83,102,127,149,161,176],"naturally":[17],"interleaves":[18],"learning":[19,142,170],"and":[20,55,93,175],"planning,":[21,52,122],"by":[22,67],"simulating":[23],"one-step":[24],"experience":[25],"update":[27],"the":[28,40,64,177],"action-value":[29],"function.":[30],"This":[31],"elegant":[32],"strategy":[34],"has":[35],"been":[36],"mostly":[37],"explored":[38],"in":[39,53,130,169,171],"tabular":[41],"setting.":[42],"The":[43],"aim":[44],"of":[45,89,186],"this":[46],"paper":[47],"revisit":[50],"sample-based":[51],"stochastic":[54,80,184],"continuous":[56,172],"domains":[57],"with":[58],"learned":[59],"models.":[60],"We":[61,100,137,159],"first":[62],"highlight":[63],"flexibility":[65],"afforded":[66],"model":[69,141],"over":[70,166],"Experience":[71,146],"Replay":[72],"(ER).":[73],"Replay-based":[74],"methods":[75,82,168],"can":[76],"be":[77],"seen":[78],"as":[79,105,124],"repeatedly":[84],"from":[86,120,132],"buffer":[88],"recent":[90],"agent-environment":[91],"interactions":[92],"perform":[94],"updates":[95],"improve":[97],"data":[98],"efficiency.":[99],"show":[101],"model,":[104],"opposed":[106],"replay":[109],"buffer,":[110],"particularly":[112],"useful":[113],"specifying":[115],"which":[116],"states":[117,126,156],"during":[121],"such":[123],"predecessor":[125],"propagate":[128],"information":[129],"reverse":[131],"state":[134,173],"more":[135],"quickly.":[136],"introduce":[138],"semi-parametric":[140],"approach,":[143],"called":[144],"Reweighted":[145],"Models":[147],"(REMs),":[148],"makes":[150],"it":[151],"simple":[152],"next":[155],"or":[157],"predecessors.":[158],"demonstrate":[160],"REM-Dyna":[162],"exhibits":[163],"similar":[164],"advantages":[165],"replay-based":[167],"problems,":[174],"performance":[178],"gap":[179],"grows":[180],"when":[181],"moving":[182],"domains,":[185],"increasing":[187],"size.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}