{"id":"https://openalex.org/W1506285364","doi":null,"title":"Practical reinforcement learning using representation learning and safe exploration for large scale Markov decision processes","display_name":"Practical reinforcement learning using representation learning and safe exploration for large scale Markov decision processes","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W1506285364","mag":"1506285364"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.951.6559","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.951.6559","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/1721.1/71455/795174743-MIT.pdf%3Bjsessionid%3D2F4272A0BCD453A6FF1568BD3FA9298C?sequence%3D2","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1721.1/71455","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059864597","display_name":"Alborz Geramifard","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Alborz Geramifard","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5059864597"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7412,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.84919041,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":95},"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/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"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.9739999771118164},{"id":"https://openalex.org/keywords/representation-learning","display_name":"representation learning","score":0.9959999918937683},{"id":"https://openalex.org/keywords/safe-exploration","display_name":"safe exploration","score":0.996999979019165},{"id":"https://openalex.org/keywords/function-approximation","display_name":"function approximation","score":0.5609999895095825},{"id":"https://openalex.org/keywords/exploration-safety","display_name":"exploration safety","score":0.33799999952316284}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7088217735290527},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6723566651344299},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5450962781906128},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5387272834777832},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5340370535850525},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.518265962600708},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5135982036590576},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2763751745223999},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14610257744789124},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08176994323730469},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.06776607036590576},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.951.6559","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.951.6559","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/1721.1/71455/795174743-MIT.pdf%3Bjsessionid%3D2F4272A0BCD453A6FF1568BD3FA9298C?sequence%3D2","raw_type":"text"},{"id":"pmh:oai:dspace.mit.edu:1721.1/71455","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/71455","pdf_url":null,"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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},{"id":"mag:1506285364","doi":null,"is_oa":false,"landing_page_url":"https://dspace.mit.edu/handle/1721.1/71455","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:1721.1/71455","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/71455","pdf_url":null,"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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":102,"referenced_works":["https://openalex.org/W15411808","https://openalex.org/W129796485","https://openalex.org/W136800639","https://openalex.org/W212314082","https://openalex.org/W1211946649","https://openalex.org/W1492518272","https://openalex.org/W1492856707","https://openalex.org/W1493947015","https://openalex.org/W1494474274","https://openalex.org/W1497290640","https://openalex.org/W1505937442","https://openalex.org/W1519179592","https://openalex.org/W1533061407","https://openalex.org/W1535030269","https://openalex.org/W1550698229","https://openalex.org/W1552830313","https://openalex.org/W1576452626","https://openalex.org/W1580530448","https://openalex.org/W1585575029","https://openalex.org/W1597317312","https://openalex.org/W1602152458","https://openalex.org/W1626155273","https://openalex.org/W1730555343","https://openalex.org/W1758031947","https://openalex.org/W1920714059","https://openalex.org/W1941445455","https://openalex.org/W1966195676","https://openalex.org/W1987600988","https://openalex.org/W1996625075","https://openalex.org/W2004229888","https://openalex.org/W2011233848","https://openalex.org/W2014932765","https://openalex.org/W2036507610","https://openalex.org/W2037090920","https://openalex.org/W2046513829","https://openalex.org/W2050882265","https://openalex.org/W2072931156","https://openalex.org/W2073384958","https://openalex.org/W2075268401","https://openalex.org/W2096712730","https://openalex.org/W2097778153","https://openalex.org/W2098102888","https://openalex.org/W2103019454","https://openalex.org/W2104641222","https://openalex.org/W2105181586","https://openalex.org/W2106321966","https://openalex.org/W2106907982","https://openalex.org/W2108581418","https://openalex.org/W2109008048","https://openalex.org/W2109718666","https://openalex.org/W2110486110","https://openalex.org/W2112264645","https://openalex.org/W2116157560","https://openalex.org/W2116339921","https://openalex.org/W2117423905","https://openalex.org/W2121627945","https://openalex.org/W2121863487","https://openalex.org/W2124175081","https://openalex.org/W2124338262","https://openalex.org/W2125074935","https://openalex.org/W2126217565","https://openalex.org/W2126410641","https://openalex.org/W2129092248","https://openalex.org/W2129442128","https://openalex.org/W2130005627","https://openalex.org/W2132351269","https://openalex.org/W2133050889","https://openalex.org/W2134461419","https://openalex.org/W2136462844","https://openalex.org/W2136602922","https://openalex.org/W2137486584","https://openalex.org/W2138326839","https://openalex.org/W2139053308","https://openalex.org/W2139418546","https://openalex.org/W2142441581","https://openalex.org/W2142544818","https://openalex.org/W2144366468","https://openalex.org/W2145510175","https://openalex.org/W2147268634","https://openalex.org/W2148150594","https://openalex.org/W2148173263","https://openalex.org/W2151661095","https://openalex.org/W2151834591","https://openalex.org/W2153353285","https://openalex.org/W2155027007","https://openalex.org/W2155791599","https://openalex.org/W2158738729","https://openalex.org/W2159476216","https://openalex.org/W2161795906","https://openalex.org/W2162418034","https://openalex.org/W2164998010","https://openalex.org/W2166295994","https://openalex.org/W2168003214","https://openalex.org/W2168359464","https://openalex.org/W2169106666","https://openalex.org/W2172968643","https://openalex.org/W2200611301","https://openalex.org/W2284626500","https://openalex.org/W2296687165","https://openalex.org/W2341171179","https://openalex.org/W2743058355","https://openalex.org/W3145128584"],"related_works":["https://openalex.org/W1570345487","https://openalex.org/W3185313117","https://openalex.org/W2995924140","https://openalex.org/W3179489233","https://openalex.org/W6922340800","https://openalex.org/W7214021569","https://openalex.org/W3005502537","https://openalex.org/W2402196364","https://openalex.org/W3003931103","https://openalex.org/W2589047632"],"abstract_inverted_index":{"Thesis":[0],"(Ph.":[1],"D.)--Massachusetts":[2],"Institute":[3],"of":[4,7],"Technology,":[5],"Dept.":[6],"Aeronautics":[8],"and":[9],"Astronautics,":[10],"2012.":[11]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}