{"id":"https://openalex.org/W2141481921","doi":"https://doi.org/10.1145/1390156.1390162","title":"Learning all optimal policies with multiple criteria","display_name":"Learning all optimal policies with multiple criteria","publication_year":2008,"publication_date":"2008-01-01","ids":{"openalex":"https://openalex.org/W2141481921","doi":"https://doi.org/10.1145/1390156.1390162","mag":"2141481921"},"language":"en","primary_location":{"id":"doi:10.1145/1390156.1390162","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390156.1390162","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th international conference on Machine learning - ICML '08","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5001779544","display_name":"Leon Barrett","orcid":"https://orcid.org/0000-0001-9896-3259"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leon Barrett","raw_affiliation_strings":["Berkeley, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Berkeley, CA","institution_ids":["https://openalex.org/I134446601"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065760252","display_name":"Srini Narayanan","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srini Narayanan","raw_affiliation_strings":["Berkeley, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Berkeley, CA","institution_ids":["https://openalex.org/I134446601"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I134446601"],"apc_list":null,"apc_paid":null,"fwci":2.2666,"has_fulltext":false,"cited_by_count":169,"citation_normalized_percentile":{"value":0.89429678,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"41","last_page":"47"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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":0.984499990940094,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9789999723434448,"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/correctness","display_name":"Correctness","score":0.7870090007781982},{"id":"https://openalex.org/keywords/weight","display_name":"Weight","score":0.7322521805763245},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7290143966674805},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.6252456903457642},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6060042381286621},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.5670403242111206},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.539578914642334},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.518580436706543},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5149698853492737},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.48413190245628357},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4233139157295227},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.42255908250808716},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38455522060394287},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.327783465385437},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.16748195886611938},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08944222331047058}],"concepts":[{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7870090007781982},{"id":"https://openalex.org/C183877218","wikidata":"https://www.wikidata.org/wiki/Q7979858","display_name":"Weight","level":3,"score":0.7322521805763245},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7290143966674805},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.6252456903457642},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6060042381286621},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.5670403242111206},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.539578914642334},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.518580436706543},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5149698853492737},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.48413190245628357},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4233139157295227},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.42255908250808716},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38455522060394287},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.327783465385437},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.16748195886611938},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08944222331047058},{"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C51568863","wikidata":"https://www.wikidata.org/wiki/Q664495","display_name":"Lie algebra","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1390156.1390162","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390156.1390162","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th international conference on Machine learning - ICML '08","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.140.2715","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.140.2715","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://leon.barrettnexus.com/papers/barrett-2008-icml-rl.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.149.6093","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.6093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://icml2008.cs.helsinki.fi/papers/257.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.218.5228","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.218.5228","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.icsi.berkeley.edu/~snarayan/icml.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W601936712","https://openalex.org/W1515851193","https://openalex.org/W1998649829","https://openalex.org/W1999874108","https://openalex.org/W2004883573","https://openalex.org/W2058432138","https://openalex.org/W2061562262","https://openalex.org/W2117428849","https://openalex.org/W2117626647","https://openalex.org/W2121863487","https://openalex.org/W2136202932","https://openalex.org/W2168359464","https://openalex.org/W2341171179"],"related_works":["https://openalex.org/W3008339103","https://openalex.org/W1667647204","https://openalex.org/W2404647514","https://openalex.org/W4247536566","https://openalex.org/W4241418540","https://openalex.org/W2018477250","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698"],"abstract_inverted_index":{"We":[0,82],"describe":[1],"an":[2,42],"algorithm":[3,37,85,113],"for":[4,24,48,70,100,114],"learning":[5,47],"in":[6,17],"the":[7,30,62,84,97,109],"presence":[8],"of":[9,52,64,73,90],"multiple":[10,31],"criteria.":[11],"Our":[12],"technique":[13],"generalizes":[14],"previous":[15],"approaches":[16],"that":[18,67,93],"it":[19],"can":[20,38],"learn":[21],"optimal":[22,98],"policies":[23],"all":[25],"linear":[26,74,102],"preference":[27,103],"assignments":[28],"over":[29],"reward":[32],"criteria":[33],"at":[34],"once.":[35],"The":[36,105],"be":[39],"viewed":[40],"as":[41],"extension":[43],"to":[44,108],"standard":[45,110],"reinforcement":[46],"MDPs":[49],"where":[50],"instead":[51],"repeatedly":[53],"backing":[54],"up":[55,61],"maximal":[56,69],"expected":[57,65],"rewards,":[58],"we":[59],"back":[60],"set":[63,72],"rewards":[66],"are":[68],"some":[71],"preferences":[75],"(given":[76],"by":[77],"a":[78,88,115],"weight":[79,117],"vector,":[80,118],"w).":[81],"present":[83],"along":[86],"with":[87],"proof":[89],"correctness":[91],"showing":[92],"our":[94],"solution":[95,106],"gives":[96],"policy":[99],"any":[101],"function.":[104],"reduces":[107],"value":[111],"iteration":[112],"specific":[116],"w.":[119]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":14},{"year":2016,"cited_by_count":12},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":6}],"updated_date":"2026-08-08T01:25:22.217667","created_date":"2025-10-10T00:00:00"}