{"id":"https://openalex.org/W4387635276","doi":"https://doi.org/10.48550/arxiv.2310.08100","title":"Generative Intrinsic Optimization: Intrinsic Control with Model Learning","display_name":"Generative Intrinsic Optimization: Intrinsic Control with Model Learning","publication_year":2023,"publication_date":"2023-10-12","ids":{"openalex":"https://openalex.org/W4387635276","doi":"https://doi.org/10.48550/arxiv.2310.08100"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2310.08100","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.08100","pdf_url":"https://arxiv.org/pdf/2310.08100","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2310.08100","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100512723","display_name":"Jianfei Ma","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ma, Jianfei","raw_affiliation_strings":["School of Mathematics and Statistics Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100512723"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/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/intrinsic-motivation","display_name":"intrinsic motivation","score":0.9620000123977661},{"id":"https://openalex.org/keywords/mutual-information","display_name":"mutual information","score":0.8050000071525574},{"id":"https://openalex.org/keywords/model-learning","display_name":"model learning","score":0.6259999871253967},{"id":"https://openalex.org/keywords/policy-iteration","display_name":"policy iteration","score":0.6790000200271606},{"id":"https://openalex.org/keywords/variational-bayesian-inference","display_name":"variational inference","score":0.8190000057220459},{"id":"https://openalex.org/keywords/sample-efficiency","display_name":"sample efficiency","score":0.6830000281333923},{"id":"https://openalex.org/keywords/uncertainty","display_name":"uncertainty","score":0.4050000011920929},{"id":"https://openalex.org/keywords/credit-assignment","display_name":"credit assignment","score":0.6890000104904175},{"id":"https://openalex.org/keywords/imitation-learning","display_name":"imitation learning","score":0.8379999995231628},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.5460000038146973}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7349408864974976},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.663316547870636},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.6364301443099976},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.5328044891357422},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5308858752250671},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5123552083969116},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.507871687412262},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.49743273854255676},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.46821096539497375},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4629206657409668},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46054500341415405},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.4507083296775818},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4387889504432678},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4139730930328369},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.25072622299194336},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12983685731887817},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.09572160243988037},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2310.08100","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.08100","pdf_url":"https://arxiv.org/pdf/2310.08100","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2310.08100","doi":"https://doi.org/10.48550/arxiv.2310.08100","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.08100","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2310.08100","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.08100","pdf_url":"https://arxiv.org/pdf/2310.08100","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Peace, justice, and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7699999809265137}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387635276.pdf","grobid_xml":"https://content.openalex.org/works/W4387635276.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2785601041","https://openalex.org/W2241417046","https://openalex.org/W2908598672","https://openalex.org/W4365211920","https://openalex.org/W2597403208","https://openalex.org/W3014948380","https://openalex.org/W4307206503","https://openalex.org/W2393900892","https://openalex.org/W4306760398","https://openalex.org/W4380551139"],"abstract_inverted_index":{"Future":[0],"sequence":[1],"represents":[2],"the":[3,7,10,13,19,50,75,81,93,98,102,127,144],"outcome":[4],"after":[5],"executing":[6],"action":[8],"into":[9,146],"environment":[11,145],"(i.e.":[12],"trajectory":[14,38],"onwards).":[15],"When":[16],"driven":[17],"by":[18],"information-theoretic":[20],"concept":[21],"of":[22,53,113,115,129,143],"mutual":[23,76,99],"information,":[24,77],"it":[25],"seeks":[26],"maximally":[27],"informative":[28],"consequences.":[29],"Explicit":[30],"outcomes":[31,114],"may":[32],"vary":[33],"across":[34],"state,":[35],"return,":[36],"or":[37,46],"serving":[39],"different":[40,111],"purposes":[41],"such":[42],"as":[43],"credit":[44],"assignment":[45],"imitation":[47],"learning.":[48],"However,":[49],"inherent":[51],"nature":[52],"incorporating":[54,110],"intrinsic":[55,131],"motivation":[56],"with":[57,133],"reward":[58],"maximization":[59],"is":[60,88],"often":[61],"neglected.":[62],"In":[63],"this":[64],"work,":[65],"we":[66,118],"propose":[67],"a":[68,85,106],"policy":[69],"iteration":[70],"scheme":[71],"that":[72],"seamlessly":[73],"incorporates":[74],"ensuring":[78],"convergence":[79],"to":[80,136],"optimal":[82],"policy.":[83],"Concurrently,":[84],"variational":[86],"approach":[87,125],"introduced,":[89],"which":[90],"jointly":[91],"learns":[92],"necessary":[94],"quantity":[95],"for":[96,109],"estimating":[97],"information":[100],"and":[101,140],"dynamics":[103],"model,":[104],"providing":[105],"general":[107],"framework":[108],"forms":[112],"interest.":[116],"While":[117],"mainly":[119],"focus":[120],"on":[121],"theoretical":[122],"analysis,":[123],"our":[124],"opens":[126],"possibilities":[128],"leveraging":[130],"control":[132],"model":[134],"learning":[135],"enhance":[137],"sample":[138],"efficiency":[139],"incorporate":[141],"uncertainty":[142],"decision-making.":[147]},"counts_by_year":[],"updated_date":"2026-10-09T09:14:12.587421","created_date":"2025-10-10T00:00:00"}