{"id":"https://openalex.org/W4416465019","doi":"https://doi.org/10.1007/978-981-95-4367-0_42","title":"Bayesian Uncertainty Estimation for\u00a0Targeted Counterfactual Experience Generation in\u00a0Reinforcement Learning","display_name":"Bayesian Uncertainty Estimation for\u00a0Targeted Counterfactual Experience Generation in\u00a0Reinforcement Learning","publication_year":2025,"publication_date":"2025-11-21","ids":{"openalex":"https://openalex.org/W4416465019","doi":"https://doi.org/10.1007/978-981-95-4367-0_42"},"language":"en","primary_location":{"id":"doi:10.1007/978-981-95-4367-0_42","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-95-4367-0_42","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/A5013829243","display_name":"Lian Tong","orcid":"https://orcid.org/0000-0002-6267-4903"},"institutions":[{"id":"https://openalex.org/I198357462","display_name":"Changsha University","ror":"https://ror.org/011d8sm39","country_code":"CN","type":"education","lineage":["https://openalex.org/I198357462"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lian Tong","raw_affiliation_strings":["School of Computer Science and Engineering, Changsha University, Changsha, 410022, China"],"raw_orcid":"https://orcid.org/0000-0002-6267-4903","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Changsha University, Changsha, 410022, China","institution_ids":["https://openalex.org/I198357462"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109439314","display_name":"Yongjun Yan","orcid":"https://orcid.org/0009-0002-8495-417X"},"institutions":[{"id":"https://openalex.org/I49934816","display_name":"Hunan University of Technology","ror":"https://ror.org/04j3vr751","country_code":"CN","type":"education","lineage":["https://openalex.org/I49934816"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongjun Yan","raw_affiliation_strings":["School of Computer Science and Artificial Intelligence, Hunan University of Technology, Zhuzhou, 412007, China"],"raw_orcid":"https://orcid.org/0009-0002-8495-417X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Hunan University of Technology, Zhuzhou, 412007, China","institution_ids":["https://openalex.org/I49934816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017533636","display_name":"Xiaoyu Zhu","orcid":"https://orcid.org/0000-0002-6815-3754"},"institutions":[{"id":"https://openalex.org/I198357462","display_name":"Changsha University","ror":"https://ror.org/011d8sm39","country_code":"CN","type":"education","lineage":["https://openalex.org/I198357462"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyu Zhu","raw_affiliation_strings":["School of Computer Science and Engineering, Changsha University, Changsha, 410022, China"],"raw_orcid":"https://orcid.org/0000-0002-6815-3754","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Changsha University, Changsha, 410022, China","institution_ids":["https://openalex.org/I198357462"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhiqiang Wen","orcid":"https://orcid.org/0000-0002-1463-4165"},"institutions":[{"id":"https://openalex.org/I49934816","display_name":"Hunan University of Technology","ror":"https://ror.org/04j3vr751","country_code":"CN","type":"education","lineage":["https://openalex.org/I49934816"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiang Wen","raw_affiliation_strings":["School of Computer Science and Artificial Intelligence, Hunan University of Technology, Zhuzhou, 412007, China"],"raw_orcid":"https://orcid.org/0000-0002-1463-4165","affiliations":[{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Hunan University of Technology, Zhuzhou, 412007, China","institution_ids":["https://openalex.org/I49934816"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065315660","display_name":"Zhigang Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I198357462","display_name":"Changsha University","ror":"https://ror.org/011d8sm39","country_code":"CN","type":"education","lineage":["https://openalex.org/I198357462"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhigang Meng","raw_affiliation_strings":["School of Computer Science and Engineering, Changsha University, Changsha, 410022, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Changsha University, Changsha, 410022, China","institution_ids":["https://openalex.org/I198357462"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5013829243"],"corresponding_institution_ids":["https://openalex.org/I198357462"],"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":0.56281598,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"625","last_page":"639"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7021999955177307,"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":0.7021999955177307,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.04560000076889992,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.02889999933540821,"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/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.982200026512146},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7297000288963318},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5575000047683716},{"id":"https://openalex.org/keywords/thompson-sampling","display_name":"Thompson sampling","score":0.45649999380111694},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4562999904155731},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4410000145435333},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4277999997138977},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.3727000057697296}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.982200026512146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.803600013256073},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7297000288963318},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.646399974822998},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5575000047683716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5403000116348267},{"id":"https://openalex.org/C73602740","wikidata":"https://www.wikidata.org/wiki/Q7795822","display_name":"Thompson sampling","level":3,"score":0.45649999380111694},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4562999904155731},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4410000145435333},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4277999997138977},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.3727000057697296},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.36970001459121704},{"id":"https://openalex.org/C68022304","wikidata":"https://www.wikidata.org/wiki/Q842217","display_name":"Bayes estimator","level":3,"score":0.33079999685287476},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.32989999651908875},{"id":"https://openalex.org/C71889745","wikidata":"https://www.wikidata.org/wiki/Q1783264","display_name":"Counterfactual conditional","level":3,"score":0.3255999982357025},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3188000023365021},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C2780625504","wikidata":"https://www.wikidata.org/wiki/Q7625026","display_name":"Structural estimation","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.2822999954223633},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2797999978065491},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C136172866","wikidata":"https://www.wikidata.org/wiki/Q1088088","display_name":"Possible world","level":2,"score":0.26820001006126404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-981-95-4367-0_42","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-95-4367-0_42","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2761873684","https://openalex.org/W2903709398","https://openalex.org/W2968104655","https://openalex.org/W3014596384","https://openalex.org/W3111711122","https://openalex.org/W4306679387","https://openalex.org/W4408490697","https://openalex.org/W4409981887"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-11-23T00:00:00"}