{"id":"https://openalex.org/W4412733258","doi":"https://doi.org/10.1007/978-3-031-95296-8_18","title":"Uncertainty-Based Dynamic Weighted Experience Replay for\u00a0Human-in-the-Loop Deep Reinforcement Learning","display_name":"Uncertainty-Based Dynamic Weighted Experience Replay for\u00a0Human-in-the-Loop Deep Reinforcement Learning","publication_year":2025,"publication_date":"2025-07-29","ids":{"openalex":"https://openalex.org/W4412733258","doi":"https://doi.org/10.1007/978-3-031-95296-8_18"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-95296-8_18","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-95296-8_18","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/A5094103452","display_name":"\u0420\u043e\u043c\u0430\u043d \u041f\u0430\u043d\u0442\u0438\u043d","orcid":"https://orcid.org/0009-0001-2655-2992"},"institutions":[{"id":"https://openalex.org/I55383850","display_name":"Tashkent State University of Economics","ror":"https://ror.org/029t9db68","country_code":"UZ","type":"education","lineage":["https://openalex.org/I55383850"]}],"countries":["UZ"],"is_corresponding":true,"raw_author_name":"Roman Pantin","raw_affiliation_strings":["Department of Economic Theory, Tashkent State University of Economics, Tashkent, Uzbekistan"],"raw_orcid":"https://orcid.org/0009-0001-2655-2992","affiliations":[{"raw_affiliation_string":"Department of Economic Theory, Tashkent State University of Economics, Tashkent, Uzbekistan","institution_ids":["https://openalex.org/I55383850"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5116683713","display_name":"Shavkat Mamarajabov","orcid":"https://orcid.org/0000-0003-4993-3285"},"institutions":[{"id":"https://openalex.org/I55383850","display_name":"Tashkent State University of Economics","ror":"https://ror.org/029t9db68","country_code":"UZ","type":"education","lineage":["https://openalex.org/I55383850"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Shavkat Mamarajabov","raw_affiliation_strings":["Department of Economic Theory, Tashkent State University of Economics, Tashkent, Uzbekistan"],"raw_orcid":"https://orcid.org/0000-0003-4993-3285","affiliations":[{"raw_affiliation_string":"Department of Economic Theory, Tashkent State University of Economics, Tashkent, Uzbekistan","institution_ids":["https://openalex.org/I55383850"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5094103452"],"corresponding_institution_ids":["https://openalex.org/I55383850"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31485432,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"196","last_page":"202"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9857000112533569,"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":0.9857000112533569,"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/T10917","display_name":"Smart Grid Security and Resilience","score":0.9735999703407288,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.9685999751091003,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.867823600769043},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8609474301338196},{"id":"https://openalex.org/keywords/human-in-the-loop","display_name":"Human-in-the-loop","score":0.6491491198539734},{"id":"https://openalex.org/keywords/loop","display_name":"Loop (graph theory)","score":0.6218425631523132},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5641467571258545},{"id":"https://openalex.org/keywords/feedback-loop","display_name":"Feedback loop","score":0.49563276767730713},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.08581233024597168},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0451200008392334}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.867823600769043},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8609474301338196},{"id":"https://openalex.org/C2780626000","wikidata":"https://www.wikidata.org/wiki/Q5936775","display_name":"Human-in-the-loop","level":2,"score":0.6491491198539734},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.6218425631523132},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5641467571258545},{"id":"https://openalex.org/C186886427","wikidata":"https://www.wikidata.org/wiki/Q5441213","display_name":"Feedback loop","level":2,"score":0.49563276767730713},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.08581233024597168},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0451200008392334},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-95296-8_18","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-95296-8_18","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":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2101911972","https://openalex.org/W2796864868","https://openalex.org/W2994446013","https://openalex.org/W3008776678","https://openalex.org/W3011016396","https://openalex.org/W3049652862","https://openalex.org/W4282944694","https://openalex.org/W4300110528","https://openalex.org/W4388096565","https://openalex.org/W4391399751","https://openalex.org/W4396878694","https://openalex.org/W4398232045","https://openalex.org/W4399031164","https://openalex.org/W4399082019"],"related_works":["https://openalex.org/W4367173559","https://openalex.org/W4409348652","https://openalex.org/W4404795748","https://openalex.org/W4405627308","https://openalex.org/W4404893116","https://openalex.org/W4288099294","https://openalex.org/W2375499102","https://openalex.org/W2381125525","https://openalex.org/W3084132679","https://openalex.org/W4301401229"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}