{"id":"https://openalex.org/W4312303305","doi":"https://doi.org/10.1109/icdl53763.2022.9962188","title":"Learning Intrinsically Motivated Transition Models for Autonomous Systems","display_name":"Learning Intrinsically Motivated Transition Models for Autonomous Systems","publication_year":2022,"publication_date":"2022-09-12","ids":{"openalex":"https://openalex.org/W4312303305","doi":"https://doi.org/10.1109/icdl53763.2022.9962188"},"language":"en","primary_location":{"id":"doi:10.1109/icdl53763.2022.9962188","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdl53763.2022.9962188","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Development and Learning (ICDL)","raw_type":"proceedings-article"},"type":"article","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/A5061856423","display_name":"Khoshrav Doctor","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]},{"id":"https://openalex.org/I177605424","display_name":"Amherst College","ror":"https://ror.org/028vqfs63","country_code":"US","type":"education","lineage":["https://openalex.org/I177605424"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Khoshrav Doctor","raw_affiliation_strings":["University of Massachusetts Amherst,Manning College of Information and Computer Science","Manning College of Information and Computer Science, University of Massachusetts Amherst"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst,Manning College of Information and Computer Science","institution_ids":["https://openalex.org/I177605424","https://openalex.org/I24603500"]},{"raw_affiliation_string":"Manning College of Information and Computer Science, University of Massachusetts Amherst","institution_ids":["https://openalex.org/I177605424","https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078407112","display_name":"Hia Ghosh","orcid":"https://orcid.org/0000-0003-0515-2938"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]},{"id":"https://openalex.org/I177605424","display_name":"Amherst College","ror":"https://ror.org/028vqfs63","country_code":"US","type":"education","lineage":["https://openalex.org/I177605424"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hia Ghosh","raw_affiliation_strings":["University of Massachusetts Amherst,Manning College of Information and Computer Science","Manning College of Information and Computer Science, University of Massachusetts Amherst"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst,Manning College of Information and Computer Science","institution_ids":["https://openalex.org/I177605424","https://openalex.org/I24603500"]},{"raw_affiliation_string":"Manning College of Information and Computer Science, University of Massachusetts Amherst","institution_ids":["https://openalex.org/I177605424","https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111628193","display_name":"Roderic A. Grupen","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]},{"id":"https://openalex.org/I177605424","display_name":"Amherst College","ror":"https://ror.org/028vqfs63","country_code":"US","type":"education","lineage":["https://openalex.org/I177605424"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roderic Grupen","raw_affiliation_strings":["University of Massachusetts Amherst,Manning College of Information and Computer Science","Manning College of Information and Computer Science, University of Massachusetts Amherst"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst,Manning College of Information and Computer Science","institution_ids":["https://openalex.org/I177605424","https://openalex.org/I24603500"]},{"raw_affiliation_string":"Manning College of Information and Computer Science, University of Massachusetts Amherst","institution_ids":["https://openalex.org/I177605424","https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5061856423"],"corresponding_institution_ids":["https://openalex.org/I177605424","https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13255458,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9147999882698059,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9147999882698059,"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/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.7265309691429138},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6763078570365906},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6268560886383057},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5582157373428345},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5424433946609497},{"id":"https://openalex.org/keywords/graphical-model","display_name":"Graphical model","score":0.4418849050998688},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4292903542518616},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4221895933151245},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.3445446491241455},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.2788269519805908},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16084212064743042}],"concepts":[{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.7265309691429138},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6763078570365906},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6268560886383057},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5582157373428345},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5424433946609497},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.4418849050998688},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4292903542518616},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4221895933151245},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3445446491241455},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.2788269519805908},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16084212064743042},{"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":"doi:10.1109/icdl53763.2022.9962188","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdl53763.2022.9962188","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Development and Learning (ICDL)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W1589140671","https://openalex.org/W1515117609","https://openalex.org/W4323315247","https://openalex.org/W2294884454","https://openalex.org/W3169161914","https://openalex.org/W4321379664","https://openalex.org/W2211790881"],"abstract_inverted_index":{"To":[0,37],"support":[1,38],"long-term":[2],"autonomy":[3],"and":[4,14,34,55,65,101,125],"rational":[5],"decision":[6],"making,":[7],"robotic":[8],"systems":[9],"should":[10],"be":[11,47,70,171],"risk":[12,76],"aware":[13,71],"actively":[15],"maintain":[16],"the":[17,51,67,73,123,129,135,150,158,162],"fidelity":[18],"of":[19,43,72,75,128,138,149,161],"critical":[20],"state":[21],"information.":[22],"This":[23],"is":[24,99,143],"particularly":[25],"difficult":[26],"in":[27,95,122],"natural":[28],"environments":[29],"that":[30,98,115,133,157],"are":[31],"dynamic,":[32],"noisy,":[33],"partially":[35],"observable.":[36],"autonomy,":[39],"predictive":[40],"probabilistic":[41,92],"models":[42,148],"robot-object":[44],"interaction":[45],"can":[46,170],"used":[48,144],"to":[49,69,90,145],"guide":[50],"agent":[52,68],"toward":[53],"rewarding":[54],"controllable":[56],"outcomes":[57],"with":[58,78],"high":[59],"probability":[60,119,152],"while":[61],"avoiding":[62],"undesired":[63],"states":[64],"allowing":[66],"amount":[74],"associated":[77],"acting.":[79],"In":[80],"this":[81],"paper,":[82],"we":[83],"propose":[84],"an":[85,139],"intrinsically":[86,175],"motivated":[87,176],"learning":[88,178],"technique":[89],"model":[91,105],"transition":[93,118,151,159],"functions":[94,120],"a":[96],"manner":[97],"task-independent":[100],"sample":[102],"efficient.":[103],"We":[104],"them":[106],"as":[107],"Aspect":[108],"Transition":[109],"Graphs":[110],"(ATGs)\u2014a":[111],"state-dependent":[112],"control":[113],"roadmap":[114],"depends":[116],"on":[117],"grounded":[121],"sensory":[124],"motor":[126],"resources":[127],"robot.":[130],"Experimental":[131],"data":[132],"changes":[134],"relative":[136],"perspective":[137],"actively-controlled":[140],"RGB-D":[141],"camera":[142],"train":[146],"empirical":[147],"functions.":[153],"Our":[154],"experiments":[155],"demonstrate":[156],"function":[160],"underlying":[163],"Partially":[164],"Observable":[165],"Markov":[166],"Decision":[167],"Process":[168],"(POMDP)":[169],"acquired":[172],"efficiently":[173],"using":[174],"structure":[177],"approach.":[179]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}