{"id":"https://openalex.org/W2097668489","doi":null,"title":"Goal-Based Imitation as Probabilistic Inference over Graphical Models","display_name":"Goal-Based Imitation as Probabilistic Inference over Graphical Models","publication_year":2005,"publication_date":"2005-12-05","ids":{"openalex":"https://openalex.org/W2097668489","mag":"2097668489"},"language":"en","primary_location":{"id":"mag:2097668489","doi":null,"is_oa":false,"landing_page_url":"http://papers.nips.cc/paper/2956-goal-based-imitation-as-probabilistic-inference-over-graphical-models.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/A5084181171","display_name":"Deepak Kumar Verma","orcid":"https://orcid.org/0000-0001-7177-7632","observed_orcids":["https://orcid.org/0000-0001-7177-7632"]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deepak Kumar Verma","raw_affiliation_strings":["Deptt of CSE, Univ. of Washington, Seattle WA#TAB#"],"raw_orcid":"https://orcid.org/0000-0001-7177-7632","affiliations":[{"raw_affiliation_string":"Deptt of CSE, Univ. of Washington, Seattle WA#TAB#","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002759219","display_name":"Rajesh P. N. Rao","orcid":"https://orcid.org/0000-0003-0682-8952","observed_orcids":["https://orcid.org/0000-0003-0682-8952"]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajesh P. N. Rao","raw_affiliation_strings":["Deptt of CSE, Univ. of Washington, Seattle WA#TAB#"],"raw_orcid":"https://orcid.org/0000-0003-0682-8952","affiliations":[{"raw_affiliation_string":"Deptt of CSE, Univ. of Washington, Seattle WA#TAB#","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":null,"apc_paid":null,"fwci":4.662,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":{"value":0.94417258,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":"18","issue":null,"first_page":"1393","last_page":"1400"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9707000255584717,"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":0.9707000255584717,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.015699999406933784,"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":0.0044999998062849045,"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/probabilistic-graphical-models","display_name":"probabilistic graphical models","score":0.8489999771118164},{"id":"https://openalex.org/keywords/probabilistic-inference","display_name":"probabilistic inference","score":0.7059999704360962},{"id":"https://openalex.org/keywords/action-planning","display_name":"action planning","score":0.671999990940094},{"id":"https://openalex.org/keywords/goal-inference","display_name":"goal inference","score":0.8349999785423279},{"id":"https://openalex.org/keywords/policy-learning","display_name":"policy learning","score":0.4659999907016754},{"id":"https://openalex.org/keywords/maze-navigation","display_name":"maze navigation","score":0.796999990940094},{"id":"https://openalex.org/keywords/human-robot-interaction","display_name":"human-robot interaction","score":0.4869999885559082},{"id":"https://openalex.org/keywords/imitation-learning","display_name":"imitation learning","score":0.36000001430511475}],"concepts":[{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.7753416299819946},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7750648856163025},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.7604634165763855},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7575399875640869},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7423518300056458},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6366562843322754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6202395558357239},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5796269774436951},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4564128518104553},{"id":"https://openalex.org/C9586889","wikidata":"https://www.wikidata.org/wiki/Q5575167","display_name":"Goal modeling","level":4,"score":0.4414197504520416},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38348525762557983},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11754932999610901},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.07704901695251465},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06977429986000061},{"id":"https://openalex.org/C6604083","wikidata":"https://www.wikidata.org/wiki/Q376937","display_name":"Requirements engineering","level":3,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2097668489","doi":null,"is_oa":false,"landing_page_url":"http://papers.nips.cc/paper/2956-goal-based-imitation-as-probabilistic-inference-over-graphical-models.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":18,"referenced_works":["https://openalex.org/W143632683","https://openalex.org/W1515851193","https://openalex.org/W1531166221","https://openalex.org/W1554672230","https://openalex.org/W1561028014","https://openalex.org/W1636244751","https://openalex.org/W1865529366","https://openalex.org/W1981578159","https://openalex.org/W2051060617","https://openalex.org/W2060993602","https://openalex.org/W2061504687","https://openalex.org/W2069384692","https://openalex.org/W2108391437","https://openalex.org/W2120360759","https://openalex.org/W2121863487","https://openalex.org/W2166302491","https://openalex.org/W2408670836","https://openalex.org/W4252491629"],"related_works":["https://openalex.org/W7098182883","https://openalex.org/W115630239","https://openalex.org/W1490071011","https://openalex.org/W2546983514","https://openalex.org/W7099230113","https://openalex.org/W2173708377","https://openalex.org/W2896583015","https://openalex.org/W3132820704","https://openalex.org/W3185606317","https://openalex.org/W2078464739"],"abstract_inverted_index":{"Humans":[0],"are":[1,147],"extremely":[2],"adept":[3],"at":[4],"learning":[5,95],"new":[6],"skills":[7],"by":[8,99],"imitating":[9],"the":[10,44,67,94,103,133,141,145,150],"actions":[11,59,75],"of":[12,16,27,46,54,66,96,135],"others.":[13],"A":[14],"progression":[15],"imitative":[17],"abilities":[18],"has":[19],"been":[20],"observed":[21,137],"in":[22],"children,":[23],"ranging":[24],"from":[25,102],"imitation":[26,33,48],"simple":[28,122],"body":[29],"movements":[30],"to":[31,76,92,112,116],"goal-based":[32,47,118],"based":[34],"on":[35],"inferring":[36,55],"intent.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41,126],"show":[42],"that":[43],"problem":[45],"can":[49,89,131],"be":[50,90,113],"formulated":[51],"as":[52],"one":[53],"goals":[56,134,146],"and":[57,139,149],"selecting":[58],"using":[60,81],"a":[61,78,121],"learned":[62],"probabilistic":[63,82],"graphical":[64,107],"model":[65,108],"environment.":[68,104],"We":[69,84],"first":[70],"describe":[71,86],"algorithms":[72],"for":[73],"planning":[74,88],"achieve":[77],"goal":[79],"state":[80],"inference.":[83],"then":[85,110],"how":[87,128],"used":[91],"bootstrap":[93],"goal-dependent":[97],"policies":[98],"utilizing":[100],"feedback":[101],"The":[105],"resulting":[106],"is":[109,152],"shown":[111],"powerful":[114],"enough":[115],"allow":[117],"imitation.":[119],"Using":[120],"maze":[123],"navigation":[124],"task,":[125],"illustrate":[127],"an":[129,136],"agent":[130],"infer":[132],"teacher":[138,142],"imitate":[140],"even":[143],"when":[144],"uncertain":[148],"demonstration":[151],"incomplete.":[153]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":4}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2016-06-24T00:00:00"}