{"id":"https://openalex.org/W2033976720","doi":null,"title":"Importance sampling for reinforcement learning with multiple objectives","display_name":"Importance sampling for reinforcement learning with multiple objectives","publication_year":2001,"publication_date":"2001-01-01","ids":{"openalex":"https://openalex.org/W2033976720","mag":"2033976720"},"language":"en","primary_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/5568","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/5568","pdf_url":"http://hdl.handle.net/1721.1/5568","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1721.1/5568","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091230938","display_name":"Christian Robert Shelton","orcid":"https://orcid.org/0000-0001-6698-7838","observed_orcids":["https://orcid.org/0000-0001-6698-7838"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christian R. Shelton","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-6698-7838","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5001833084","display_name":"Tomaso Poggio","orcid":"https://orcid.org/0000-0002-3944-0455","observed_orcids":["https://orcid.org/0000-0002-3944-0455"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomaso Poggio","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-3944-0455","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4086,"has_fulltext":true,"cited_by_count":69,"citation_normalized_percentile":{"value":0.89399076,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":99},"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.0,"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"}},{"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/importance-sampling","display_name":"importance sampling","score":0.9950000047683716},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.9350000023841858},{"id":"https://openalex.org/keywords/multi-objective-reinforcement-learning","display_name":"multi-objective reinforcement learning","score":0.8659999966621399},{"id":"https://openalex.org/keywords/multi-criteria-decision-making","display_name":"multi-criteria decision making","score":0.6579999923706055}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.873870849609375},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.6602697372436523},{"id":"https://openalex.org/C2779110517","wikidata":"https://www.wikidata.org/wiki/Q1240788","display_name":"Supervisor","level":2,"score":0.6555994153022766},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6229544878005981},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5722447633743286},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5618058443069458},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.5079143643379211},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4661352038383484},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.45486515760421753},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4406135678291321},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41925594210624695},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3928508162498474},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3688613772392273},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3120744824409485},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15392115712165833},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.13965237140655518},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","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}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:dspace.mit.edu:1721.1/5568","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/5568","pdf_url":"http://hdl.handle.net/1721.1/5568","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},{"id":"pmh:oai:dspace.mit.edu:1721.1/86774","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/86774","pdf_url":"http://hdl.handle.net/1721.1/86774","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1017.7083","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1017.7083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dspace.mit.edu/bitstream/handle/1721.1/86774/49837623-MIT.pdf%3Bjsessionid%3DE38DCCDAEBE50FF7B5AF913A5D1E891C?sequence%3D2","raw_type":"text"},{"id":"mag:2033976720","doi":null,"is_oa":false,"landing_page_url":"http://cbcl.mit.edu/publications/theses/thesis-shelton.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/5568","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/5568","pdf_url":"http://hdl.handle.net/1721.1/5568","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3313949225","display_name":"Adaptive Man-Machine Interfaces","funder_award_id":"9800032","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6394687995","display_name":"ITR: From Bits to Information: Statistical Learning Technologies for Digital Information Management and Search","funder_award_id":"0085836","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8076890045","display_name":"KDI: Learning of Objects and Object Classes in Visual Cortex","funder_award_id":"9872936","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320322622","display_name":"Toyota Motor Corporation","ror":"https://ror.org/02zqm6r10"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2033976720.pdf","grobid_xml":"https://content.openalex.org/works/W2033976720.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W6242441","https://openalex.org/W1514587017","https://openalex.org/W1515891729","https://openalex.org/W1554663460","https://openalex.org/W1557760016","https://openalex.org/W1576452626","https://openalex.org/W1593706890","https://openalex.org/W1596364083","https://openalex.org/W1599491685","https://openalex.org/W1600046456","https://openalex.org/W1601974704","https://openalex.org/W1640774615","https://openalex.org/W1657542410","https://openalex.org/W1748709110","https://openalex.org/W1981329484","https://openalex.org/W1985808284","https://openalex.org/W2000836282","https://openalex.org/W2025268472","https://openalex.org/W2043881376","https://openalex.org/W2057565703","https://openalex.org/W2058209938","https://openalex.org/W2094509095","https://openalex.org/W2107726111","https://openalex.org/W2109690032","https://openalex.org/W2117428849","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2125074935","https://openalex.org/W2125838338","https://openalex.org/W2133727275","https://openalex.org/W2137466452","https://openalex.org/W2147632348","https://openalex.org/W2149126181","https://openalex.org/W2151726636","https://openalex.org/W2155027007","https://openalex.org/W2156737235","https://openalex.org/W2158145505","https://openalex.org/W2160067530","https://openalex.org/W2161521419","https://openalex.org/W2164056559"],"related_works":["https://openalex.org/W7095515947","https://openalex.org/W2189549406","https://openalex.org/W3108042666","https://openalex.org/W6983603159","https://openalex.org/W3082245592","https://openalex.org/W7101001091","https://openalex.org/W2402196364","https://openalex.org/W2560963682","https://openalex.org/W2042296018","https://openalex.org/W2775961077"],"abstract_inverted_index":{"Thesis":[0],"(Ph.":[1],"D.)--Massachusetts":[2],"Institute":[3],"of":[4,7],"Technology,":[5],"Dept.":[6],"Electrical":[8],"Engineering":[9],"and":[10],"Computer":[11],"Science,":[12],"2001.":[13]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2016-06-24T00:00:00"}