{"id":"https://openalex.org/W4388574051","doi":"https://doi.org/10.1007/978-3-031-47705-8_14","title":"Reinforcement Learning Under Partial Observability Guided by\u00a0Learned Environment Models","display_name":"Reinforcement Learning Under Partial Observability Guided by\u00a0Learned Environment Models","publication_year":2023,"publication_date":"2023-11-06","ids":{"openalex":"https://openalex.org/W4388574051","doi":"https://doi.org/10.1007/978-3-031-47705-8_14"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-47705-8_14","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-47705-8_14","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5040586809","display_name":"Edi Mu\u0161kardin","orcid":"https://orcid.org/0000-0001-8089-5024"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]},{"id":"https://openalex.org/I4210123126","display_name":"Silicon Austria Labs (Austria)","ror":"https://ror.org/03b1qgn79","country_code":"AT","type":"company","lineage":["https://openalex.org/I4210123126"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Edi Mu\u0161kardin","raw_affiliation_strings":["Graz University of Technology, Institute of Software Technology, Graz, Austria","Silicon Austria Labs, TU Graz - SAL DES Lab, Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Graz University of Technology, Institute of Software Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]},{"raw_affiliation_string":"Silicon Austria Labs, TU Graz - SAL DES Lab, Graz, Austria","institution_ids":["https://openalex.org/I4210123126","https://openalex.org/I4092182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078635542","display_name":"Martin Tappler","orcid":"https://orcid.org/0000-0002-4193-5609"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]},{"id":"https://openalex.org/I4210123126","display_name":"Silicon Austria Labs (Austria)","ror":"https://ror.org/03b1qgn79","country_code":"AT","type":"company","lineage":["https://openalex.org/I4210123126"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Martin Tappler","raw_affiliation_strings":["Graz University of Technology, Institute of Software Technology, Graz, Austria","Silicon Austria Labs, TU Graz - SAL DES Lab, Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Graz University of Technology, Institute of Software Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]},{"raw_affiliation_string":"Silicon Austria Labs, TU Graz - SAL DES Lab, Graz, Austria","institution_ids":["https://openalex.org/I4210123126","https://openalex.org/I4092182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009450062","display_name":"Bernhard K. Aichernig","orcid":"https://orcid.org/0000-0002-3484-5584"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Bernhard K. Aichernig","raw_affiliation_strings":["Graz University of Technology, Institute of Software Technology, Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Graz University of Technology, Institute of Software Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046899369","display_name":"Ingo Pill","orcid":"https://orcid.org/0000-0002-8420-6377"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]},{"id":"https://openalex.org/I4210123126","display_name":"Silicon Austria Labs (Austria)","ror":"https://ror.org/03b1qgn79","country_code":"AT","type":"company","lineage":["https://openalex.org/I4210123126"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Ingo Pill","raw_affiliation_strings":["Silicon Austria Labs, TU Graz - SAL DES Lab, Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Silicon Austria Labs, TU Graz - SAL DES Lab, Graz, Austria","institution_ids":["https://openalex.org/I4210123126","https://openalex.org/I4092182"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5040586809"],"corresponding_institution_ids":["https://openalex.org/I4092182","https://openalex.org/I4210123126"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":2.6393,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.91593799,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"257","last_page":"276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9927999973297119,"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/T10142","display_name":"Formal Methods in Verification","score":0.9810000061988831,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.9469413161277771},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8796721696853638},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8009909391403198},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.73613041639328},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6821280717849731},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6294594407081604},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.516065776348114},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4660915434360504},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4491276443004608},{"id":"https://openalex.org/keywords/complete-information","display_name":"Complete information","score":0.42942798137664795},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41152215003967285},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.35366010665893555},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.2845418453216553},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15059301257133484},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09171202778816223}],"concepts":[{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.9469413161277771},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8796721696853638},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8009909391403198},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.73613041639328},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6821280717849731},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6294594407081604},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.516065776348114},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4660915434360504},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4491276443004608},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.42942798137664795},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41152215003967285},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.35366010665893555},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.2845418453216553},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15059301257133484},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09171202778816223},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","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},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-47705-8_14","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-47705-8_14","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W174941419","https://openalex.org/W1482467703","https://openalex.org/W1486103693","https://openalex.org/W1541084404","https://openalex.org/W1555801537","https://openalex.org/W2083808302","https://openalex.org/W2260756217","https://openalex.org/W2406438973","https://openalex.org/W2494400401","https://openalex.org/W2595840341","https://openalex.org/W2972500268","https://openalex.org/W2996875168","https://openalex.org/W2997022832","https://openalex.org/W3097686825","https://openalex.org/W3105078582","https://openalex.org/W3173218700","https://openalex.org/W3175871729","https://openalex.org/W3197209873","https://openalex.org/W3206503929","https://openalex.org/W3215640983","https://openalex.org/W4233413206","https://openalex.org/W4310895557","https://openalex.org/W4312510909","https://openalex.org/W4382318502","https://openalex.org/W6637967152","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W11481024","https://openalex.org/W2999848267","https://openalex.org/W2096013579","https://openalex.org/W1589140671","https://openalex.org/W1760611253","https://openalex.org/W52153049","https://openalex.org/W2951545791","https://openalex.org/W1515117609","https://openalex.org/W2294884454","https://openalex.org/W4323315247"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-29T08:15:47.926485","created_date":"2025-10-10T00:00:00"}
