{"id":"https://openalex.org/W2966675798","doi":"https://doi.org/10.24963/ijcai.2019/506","title":"Planning with Expectation Models","display_name":"Planning with Expectation Models","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2966675798","doi":"https://doi.org/10.24963/ijcai.2019/506","mag":"2966675798"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/506","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/506","pdf_url":"https://www.ijcai.org/proceedings/2019/0506.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth 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/2019/0506.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023807422","display_name":"Yi Wan","orcid":"https://orcid.org/0000-0002-8983-3839"},"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":true,"raw_author_name":"Yi Wan","raw_affiliation_strings":["Reinforcement Learning and Artificial Intelligence Laboratory, University of Alberta"],"affiliations":[{"raw_affiliation_string":"Reinforcement Learning and Artificial Intelligence Laboratory, University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101974047","display_name":"Muhammad Zaheer","orcid":"https://orcid.org/0000-0001-9199-5880"},"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":["Reinforcement Learning and Artificial Intelligence Laboratory, University of Alberta"],"affiliations":[{"raw_affiliation_string":"Reinforcement Learning and Artificial Intelligence Laboratory, University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108583544","display_name":"Adam White","orcid":null},"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":"Adam White","raw_affiliation_strings":["Reinforcement Learning and Artificial Intelligence Laboratory, University of Alberta"],"affiliations":[{"raw_affiliation_string":"Reinforcement Learning and Artificial Intelligence Laboratory, University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","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":["Reinforcement Learning and Artificial Intelligence Laboratory, University of Alberta"],"affiliations":[{"raw_affiliation_string":"Reinforcement Learning and Artificial Intelligence Laboratory, University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004923102","display_name":"Richard S. Sutton","orcid":"https://orcid.org/0000-0002-3679-3415"},"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":"Richard S. Sutton","raw_affiliation_strings":["Reinforcement Learning and Artificial Intelligence Laboratory, University of Alberta"],"affiliations":[{"raw_affiliation_string":"Reinforcement Learning and Artificial Intelligence Laboratory, University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5023807422"],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":0.7001,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77913035,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3649","last_page":"3655"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9778000116348267,"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/T10142","display_name":"Formal Methods in Verification","score":0.9697999954223633,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7598224878311157},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6163066029548645},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5886739492416382},{"id":"https://openalex.org/keywords/parametrization","display_name":"Parametrization (atmospheric modeling)","score":0.5489524006843567},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.49572575092315674},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4676593840122223},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4394325315952301},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.42748868465423584},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4038841426372528},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3262026906013489},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2248268723487854}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7598224878311157},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6163066029548645},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5886739492416382},{"id":"https://openalex.org/C202887219","wikidata":"https://www.wikidata.org/wiki/Q3895221","display_name":"Parametrization (atmospheric modeling)","level":3,"score":0.5489524006843567},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.49572575092315674},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4676593840122223},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4394325315952301},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.42748868465423584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4038841426372528},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3262026906013489},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2248268723487854},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C74902906","wikidata":"https://www.wikidata.org/wiki/Q1190858","display_name":"Radiative transfer","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2019/506","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/506","pdf_url":"https://www.ijcai.org/proceedings/2019/0506.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/506","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/506","pdf_url":"https://www.ijcai.org/proceedings/2019/0506.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth 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/W2966675798.pdf","grobid_xml":"https://content.openalex.org/works/W2966675798.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1646707810","https://openalex.org/W1714211023","https://openalex.org/W2075268401","https://openalex.org/W2106261932","https://openalex.org/W2109910161","https://openalex.org/W2114384389","https://openalex.org/W2118688707","https://openalex.org/W2123979492","https://openalex.org/W2124175081","https://openalex.org/W2132622533","https://openalex.org/W2140135625","https://openalex.org/W2154761920","https://openalex.org/W2159752377","https://openalex.org/W2898155524","https://openalex.org/W2910907894","https://openalex.org/W2950517718","https://openalex.org/W2950872548","https://openalex.org/W2963224068","https://openalex.org/W2963473026","https://openalex.org/W2963582482","https://openalex.org/W4214717370","https://openalex.org/W4245108548","https://openalex.org/W4289303880","https://openalex.org/W4298206671"],"related_works":["https://openalex.org/W2153421756","https://openalex.org/W2054489697","https://openalex.org/W2077818434","https://openalex.org/W2361081803","https://openalex.org/W2036241269","https://openalex.org/W2109057766","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698"],"abstract_inverted_index":{"Distribution":[0],"and":[1,25,45,131,143,148],"sample":[2],"models":[3,17,63,88],"are":[4,28,36],"two":[5,122],"popular":[6],"model":[7,101,109],"choices":[8,125],"in":[9,117],"model-based":[10,139],"reinforcement":[11],"learning":[12,15],"(MBRL).":[13],"However,":[14],"these":[16],"can":[18,64],"be":[19,65],"intractable,":[20],"particularly":[21],"when":[22],"the":[23,33,111,128,152,155],"state":[24,112,118],"action":[26],"spaces":[27],"large.":[29],"Expectation":[30],"models,":[31,134],"on":[32],"other":[34],"hand,":[35],"relatively":[37],"easier":[38],"to":[39,42,104],"learn":[40],"due":[41],"their":[43],"compactness":[44],"have":[46],"also":[47],"been":[48],"widely":[49],"used":[50,66],"for":[51,67,89,126],"deterministic":[52],"environments.":[53],"For":[54],"stochastic":[55],"environments,":[56],"it":[57],"is":[58,102,115],"not":[59],"obvious":[60],"how":[61],"expectation":[62,87,100,133],"planning":[68,97,105,157],"as":[69],"they":[70],"only":[71],"partially":[72],"characterize":[73],"a":[74,81,107,137],"distribution.":[75],"In":[76,91],"this":[77],"paper,":[78],"we":[79,93],"propose":[80,136],"sound":[82,138],"way":[83],"of":[84,154],"using":[85],"approximate":[86],"MBRL.":[90],"particular,":[92],"1)":[94],"show":[95],"that":[96],"with":[98,106],"an":[99],"equivalent":[103],"distribution":[108],"if":[110],"value":[113],"function":[114],"linear":[116,130],"features,":[119],"2)":[120],"analyze":[121],"common":[123],"parametrization":[124],"approximating":[127],"expectation:":[129],"non-linear":[132],"3)":[135],"policy":[140],"evaluation":[141],"algorithm":[142],"present":[144],"its":[145],"convergence":[146],"results,":[147],"4)":[149],"empirically":[150],"demonstrate":[151],"effectiveness":[153],"proposed":[156],"algorithm.":[158]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}