{"id":"https://openalex.org/W2170420157","doi":null,"title":"Information-based learning by agents in unbounded state spaces","display_name":"Information-based learning by agents in unbounded state spaces","publication_year":2014,"publication_date":"2014-12-08","ids":{"openalex":"https://openalex.org/W2170420157","mag":"2170420157"},"language":"en","primary_location":{"id":"mag:2170420157","doi":null,"is_oa":false,"landing_page_url":"https://papers.nips.cc/paper/5266-information-based-learning-by-agents-in-unbounded-state-spaces.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},"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/A5040003671","display_name":"Shariq Mobin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shariq Mobin","raw_affiliation_strings":["Redwood Center for Theoretical Neuroscience, University of California, Berkeley, Berkeley, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Redwood Center for Theoretical Neuroscience, University of California, Berkeley, Berkeley, CA#TAB#","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065975075","display_name":"James Arnemann","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Arnemann","raw_affiliation_strings":["Redwood Center for Theoretical Neuroscience, University of California, Berkeley, Berkeley, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Redwood Center for Theoretical Neuroscience, University of California, Berkeley, Berkeley, CA#TAB#","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":null,"display_name":"Fritz Sommer","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fritz Sommer","raw_affiliation_strings":["Redwood Center for Theoretical Neuroscience, University of California, Berkeley, Berkeley, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Redwood Center for Theoretical Neuroscience, University of California, Berkeley, Berkeley, CA#TAB#","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":0.5964,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75701149,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":93},"biblio":{"volume":"27","issue":null,"first_page":"3023","last_page":"3031"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8032000064849854,"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":0.8032000064849854,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.03689999878406525,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.03060000017285347,"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/information-based-learning","display_name":"information-based learning","score":0.9440000057220459},{"id":"https://openalex.org/keywords/unbounded-state-space","display_name":"unbounded state space","score":0.8450000286102295},{"id":"https://openalex.org/keywords/chinese-restaurant-process","display_name":"Chinese restaurant process","score":0.7739999890327454},{"id":"https://openalex.org/keywords/nonparametric-bayesian-models","display_name":"nonparametric Bayesian models","score":0.8600000143051147},{"id":"https://openalex.org/keywords/empirical-bayes","display_name":"empirical Bayes","score":0.8600000143051147},{"id":"https://openalex.org/keywords/exploration","display_name":"exploration","score":0.3449999988079071},{"id":"https://openalex.org/keywords/internal-models","display_name":"internal models","score":0.597000002861023}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7168000936508179},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6321069598197937},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.6299747228622437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5394225120544434},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5166971683502197},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5130199790000916},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.4780997931957245},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4513220191001892},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4387854337692261},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4063951075077057},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3909364938735962},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1973743736743927},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15695416927337646},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2170420157","doi":null,"is_oa":false,"landing_page_url":"https://papers.nips.cc/paper/5266-information-based-learning-by-agents-in-unbounded-state-spaces.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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W263845233","https://openalex.org/W615696229","https://openalex.org/W1504212531","https://openalex.org/W1505937442","https://openalex.org/W1550989509","https://openalex.org/W1562671620","https://openalex.org/W1582436621","https://openalex.org/W1606994719","https://openalex.org/W1967465043","https://openalex.org/W2013830186","https://openalex.org/W2015667537","https://openalex.org/W2053218206","https://openalex.org/W2065264265","https://openalex.org/W2078150668","https://openalex.org/W2099064293","https://openalex.org/W2115305054","https://openalex.org/W2116459397","https://openalex.org/W2120889539","https://openalex.org/W2124595631","https://openalex.org/W2125710232","https://openalex.org/W2150507172","https://openalex.org/W2341171179"],"related_works":["https://openalex.org/W2564518165","https://openalex.org/W1606994719","https://openalex.org/W7095108558","https://openalex.org/W1550989509","https://openalex.org/W4210690775","https://openalex.org/W4403799171","https://openalex.org/W2913854057","https://openalex.org/W2078150668","https://openalex.org/W2945568361","https://openalex.org/W2031571562"],"abstract_inverted_index":{"The":[0],"idea":[1],"that":[2,31,82,96],"animals":[3,49],"might":[4],"use":[5],"information-driven":[6],"planning":[7],"to":[8,91,103],"explore":[9,105],"an":[10,15,97],"unknown":[11],"environment":[12],"and":[13,50,95,107],"build":[14],"internal":[16],"model":[17,88],"of":[18,40,69],"it":[19],"has":[20,29],"been":[21],"proposed":[22],"for":[23],"quite":[24],"some":[25],"time.":[26],"Recent":[27],"work":[28],"demonstrated":[30],"agents":[32,70],"using":[33,75],"this":[34,60,93],"principle":[35],"can":[36],"efficiently":[37,104],"learn":[38],"models":[39],"probabilistic":[41],"environments":[42],"with":[43,55],"discrete,":[44],"bounded":[45,106],"state":[46,73],"spaces.":[47],"However,":[48],"robots":[51],"are":[52],"commonly":[53],"confronted":[54],"unbounded":[56,72,108],"environments.":[57],"To":[58],"address":[59],"more":[61],"challenging":[62],"situation,":[63],"we":[64,80],"study":[65],"information-based":[66],"learning":[67],"strategies":[68],"in":[71],"spaces":[74],"non-parametric":[76],"Bayesian":[77],"models.":[78],"Specifically,":[79],"demonstrate":[81],"the":[83],"Chinese":[84],"Restaurant":[85],"Process":[86],"(CRP)":[87],"is":[89,101],"able":[90,102],"solve":[92],"problem":[94],"Empirical":[98],"Bayes":[99],"version":[100],"worlds":[109],"by":[110],"relying":[111],"on":[112],"little":[113],"prior":[114],"information.":[115]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}