{"id":"https://openalex.org/W115630239","doi":null,"title":"Graphical Models for Planning and Imitation in Uncertain Environments","display_name":"Graphical Models for Planning and Imitation in Uncertain Environments","publication_year":2008,"publication_date":"2008-02-07","ids":{"openalex":"https://openalex.org/W115630239","mag":"115630239"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.81.6021","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.81.6021","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.washington.edu/homes/rao/planningTR05.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/A5084181171","display_name":"Deepak Kumar Verma","orcid":"https://orcid.org/0000-0001-7177-7632","observed_orcids":["https://orcid.org/0000-0001-7177-7632"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deepak Verma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rajesh Rao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"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":0.6758000254631042,"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":0.6758000254631042,"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":0.249099999666214,"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":0.06480000168085098,"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/planning-under-uncertainty","display_name":"planning under uncertainty","score":0.7149999737739563},{"id":"https://openalex.org/keywords/policy-learning","display_name":"policy learning","score":0.847000002861023},{"id":"https://openalex.org/keywords/dynamic-bayesian-networks","display_name":"dynamic Bayesian networks","score":0.9120000004768372},{"id":"https://openalex.org/keywords/probabilistic-inference","display_name":"probabilistic inference","score":0.746999979019165},{"id":"https://openalex.org/keywords/plan-execution","display_name":"plan execution","score":0.6060000061988831},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-processes","display_name":"partially observable Markov decision processes","score":0.8510000109672546},{"id":"https://openalex.org/keywords/learning-environment-model","display_name":"learning environment model","score":0.6110000014305115}],"concepts":[{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.7952260971069336},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7314639091491699},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6073108911514282},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5866715312004089},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5729127526283264},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5388244390487671},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.516360878944397},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.4765118658542633},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.45230013132095337},{"id":"https://openalex.org/C82142266","wikidata":"https://www.wikidata.org/wiki/Q3456604","display_name":"Dynamic Bayesian network","level":3,"score":0.44449907541275024},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.44039076566696167},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2875993549823761},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.81.6021","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.81.6021","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.washington.edu/homes/rao/planningTR05.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W23603061","https://openalex.org/W70402205","https://openalex.org/W143632683","https://openalex.org/W1554672230","https://openalex.org/W1576452626","https://openalex.org/W1636244751","https://openalex.org/W1980452149","https://openalex.org/W2032100464","https://openalex.org/W2061504687","https://openalex.org/W2120360759","https://openalex.org/W2121863487","https://openalex.org/W2408542687","https://openalex.org/W2408670836"],"related_works":["https://openalex.org/W2097668489","https://openalex.org/W7098182883","https://openalex.org/W7098054101","https://openalex.org/W7100861284","https://openalex.org/W2770014065","https://openalex.org/W2408670836","https://openalex.org/W2573514974","https://openalex.org/W2130388951","https://openalex.org/W2342302999","https://openalex.org/W2896583015"],"abstract_inverted_index":{"We":[0,51,76],"show":[1,162],"that":[2,137,163,168],"the":[3,60,69,88,91,131,138,145,156,159,164,182,197,201,204],"problems":[4],"of":[5,32,62,90,148,158,184],"planning,":[6],"policy":[7,85,106,174],"learning,":[8],"and":[9,46,71,84,105,173,194],"goal-based":[10],"imitation":[11],"can":[12,55,127,140,176],"be":[13,56,128,141,178],"addressed":[14],"within":[15,130],"a":[16,37,47,72,96,114],"unified":[17],"framework":[18],"based":[19],"on":[20],"probabilistic":[21,30],"inference":[22,31],"in":[23,36,87],"graphical":[24,132,166],"models.":[25],"Planning":[26],"is":[27],"viewed":[28],"as":[29,122],"an":[33,43,185],"action":[34],"sequence":[35],"Dynamic":[38],"Bayesian":[39],"Network":[40],"(DBN),":[41],"given":[42],"initial":[44],"state":[45],"desired":[48],"goal":[49,126],"state.":[50],"describe":[52],"how":[53],"planning":[54,104,172],"used":[57,142,170,179],"to":[58,102,125,143],"bootstrap":[59],"learning":[61,86,107,175],"goal-dependent":[63],"policies":[64],"by":[65,203],"utilizing":[66],"feedback":[67],"from":[68],"environment":[70,74],"learned":[73],"model.":[75,133],"demonstrate":[77,136],"several":[78],"different":[79],"strategies":[80],"for":[81,95,171,180,188,195],"plan":[82],"execution":[83],"context":[89],"standard":[92],"navigation":[93],"problem":[94],"stochastic":[97],"maze":[98],"environment.":[99],"In":[100],"contrast":[101],"conventional":[103],"methods,":[108],"our":[109],"approach":[110,139],"does":[111],"not":[112],"require":[113],"reward":[115],"or":[116],"utility":[117],"function,":[118],"although":[119],"constraints":[120],"such":[121],"shortest":[123],"path":[124],"incorporated":[129],"Our":[134],"results":[135],"handle":[144],"challenging":[146],"case":[147],"partially":[149],"observable":[150],"states":[151],"(e.g.,":[152],"POMDPs).":[153],"To":[154],"illustrate":[155],"versatility":[157],"approach,":[160],"we":[161],"same":[165],"model":[167],"was":[169,206],"also":[177],"inferring":[181],"goals":[183],"observed":[186],"teacher,":[187],"executing":[189],"actions":[190],"under":[191],"uncertain":[192],"goals,":[193],"imitating":[196],"teacher":[198,205],"even":[199],"when":[200],"demonstration":[202],"incomplete.":[207],"1.":[208]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-27T00:00:00"}