{"id":"https://openalex.org/W2163602945","doi":null,"title":"Reward Design via Online Gradient Ascent","display_name":"Reward Design via Online Gradient Ascent","publication_year":2010,"publication_date":"2010-12-06","ids":{"openalex":"https://openalex.org/W2163602945","mag":"2163602945"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.185.2642","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.185.2642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-personal.umich.edu/%7Erickl/pubs/sorg-singh-lewis-2010-nips.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039371251","display_name":"Jonathan Sorg","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Sorg","raw_affiliation_strings":["Computer Science and Engineering; University of Michigan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering; University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077109450","display_name":"Richard L. Lewis","orcid":"https://orcid.org/0000-0001-6403-489X","observed_orcids":["https://orcid.org/0000-0001-6403-489X"]},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard L. Lewis","raw_affiliation_strings":["Department of Psychology , University of Michigan ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Psychology , University of Michigan ,","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065366930","display_name":"Satinder Pal Singh","orcid":"https://orcid.org/0000-0002-2736-7641","observed_orcids":["https://orcid.org/0000-0002-2736-7641","https://orcid.org/0000-0002-8215-8295","https://orcid.org/0000-0002-5169-9486","https://orcid.org/0000-0001-9360-7060"]},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Satinder Singh","raw_affiliation_strings":["Computer Science and Engineering; University of Michigan"],"raw_orcid":"https://orcid.org/0000-0002-2736-7641","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering; University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":0.9061,"has_fulltext":false,"cited_by_count":71,"citation_normalized_percentile":{"value":0.78975599,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":"23","issue":null,"first_page":"2190","last_page":"2198"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T12101","display_name":"Advanced Bandit Algorithms Research","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/reward-function-design","display_name":"reward function design","score":0.7170000076293945},{"id":"https://openalex.org/keywords/convergence-guarantees","display_name":"convergence guarantees","score":0.6370000243186951},{"id":"https://openalex.org/keywords/policy-gradient","display_name":"policy gradient","score":0.6510000228881836},{"id":"https://openalex.org/keywords/autonomous-agents","display_name":"autonomous agents","score":0.6259999871253967},{"id":"https://openalex.org/keywords/goal-specification","display_name":"goal specification","score":0.48500001430511475},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.4830000102519989}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7989382743835449},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7353330850601196},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5761200189590454},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5153533816337585},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5112965106964111},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.507440984249115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44979265332221985},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44026127457618713},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.14765897393226624},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12029832601547241},{"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},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.185.2642","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.185.2642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-personal.umich.edu/%7Erickl/pubs/sorg-singh-lewis-2010-nips.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.232.3698","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.232.3698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://books.nips.cc/papers/files/nips23/NIPS2010_0956.pdf","raw_type":"text"},{"id":"mag:2163602945","doi":null,"is_oa":false,"landing_page_url":"http://books.nips.cc/papers/files/nips23/NIPS2010_0956.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1491843047","https://openalex.org/W1493671888","https://openalex.org/W1499021337","https://openalex.org/W1505937442","https://openalex.org/W1515851193","https://openalex.org/W1557073320","https://openalex.org/W1777239053","https://openalex.org/W1814308503","https://openalex.org/W1863227302","https://openalex.org/W1988526405","https://openalex.org/W2035737909","https://openalex.org/W2094387729","https://openalex.org/W2101524054","https://openalex.org/W2116442740","https://openalex.org/W2121863487","https://openalex.org/W2123408238","https://openalex.org/W2124352385","https://openalex.org/W2135995480","https://openalex.org/W2139612737","https://openalex.org/W2150617783","https://openalex.org/W2164424353","https://openalex.org/W2312609093","https://openalex.org/W2339945684","https://openalex.org/W2592535843","https://openalex.org/W2963214119","https://openalex.org/W7098082322"],"related_works":["https://openalex.org/W88199814","https://openalex.org/W2135995480","https://openalex.org/W7124276356","https://openalex.org/W2796835114","https://openalex.org/W2750866482","https://openalex.org/W4283806931","https://openalex.org/W7097961005","https://openalex.org/W2897200624","https://openalex.org/W7124287549","https://openalex.org/W2105380246"],"abstract_inverted_index":{"Recent":[0],"work":[1],"has":[2,155],"demonstrated":[3],"that":[4,108],"when":[5],"artificial":[6,41],"agents":[7,127],"are":[8],"limited":[9],"in":[10,126],"their":[11,15],"ability":[12,121],"to":[13,34,122],"achieve":[14],"goals,":[16],"the":[17,24,29,35,40,44,48,67,78,97,143,168],"agent":[18,147],"designer":[19,148,154],"can":[20],"benefit":[21],"by":[22],"making":[23],"agent\u2019s":[25,42,49,68,79,104],"goals":[26,160,166],"different":[27],"from":[28],"designer\u2019s.":[30],"This":[31],"gives":[32],"rise":[33],"optimization":[36],"problem":[37,59,100],"of":[38,75,131,145],"designing":[39,47],"goals\u2014in":[43],"RL":[45],"framework,":[46],"reward":[50,58,99,124],"function.":[51],"Existing":[52],"attempts":[53],"at":[54],"solving":[55,96],"this":[56,82,139],"optimal":[57,98],"do":[60,71],"not":[61],"leverage":[62],"experience":[63],"gained":[64],"online":[65,101],"during":[66,102],"lifetime":[69],"nor":[70],"they":[72],"take":[73],"advantage":[74],"knowledge":[76],"about":[77],"structure.":[80],"In":[81,138],"work,":[83,140],"we":[84,118,141],"develop":[85],"a":[86,112],"gradient":[87,115],"ascent":[88],"approach":[89],"with":[90,128],"formal":[91],"convergence":[92],"guarantees":[93],"for":[94,167],"approximately":[95],"an":[103,146,150],"lifetime.":[105],"We":[106],"show":[107],"our":[109],"method":[110],"generalizes":[111],"standard":[113],"policy":[114],"approach,":[116],"and":[117],"demonstrate":[119],"its":[120],"improve":[123],"functions":[125],"various":[129],"forms":[130],"limitations.":[132],"1":[133],"The":[134,153],"Optimal":[135],"Reward":[136],"Problem":[137],"consider":[142],"scenario":[144],"building":[149],"autonomous":[151,169],"agent.":[152,170],"his":[156],"or":[157],"her":[158],"own":[159],"which":[161],"must":[162],"be":[163],"translated":[164],"into":[165]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":3}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}