{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:19:25Z","timestamp":1780636765891,"version":"3.54.1"},"reference-count":56,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T00:00:00Z","timestamp":1762905600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T00:00:00Z","timestamp":1762905600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,11,12]]},"DOI":"10.1109\/tps-isa67132.2025.00045","type":"proceedings-article","created":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T20:50:15Z","timestamp":1772571015000},"page":"363-371","source":"Crossref","is-referenced-by-count":1,"title":["Guiding Reinforcement Learning Using Uncertainty-Aware Large Language Models"],"prefix":"10.1109","author":[{"given":"Maryam","family":"Shoaeinaeini","sequence":"first","affiliation":[{"name":"University of Kentucky,dept. of Computer Science,Lexington,KY,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brent","family":"Harrison","sequence":"additional","affiliation":[{"name":"University of Kentucky,dept. of Computer Science,Lexington,KY,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/820"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-7784-8_10"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-41188-6_3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102738"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3150802"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.65109\/FMRF8293"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1597735.1597738"},{"key":"ref9","first-page":"2285","article-title":"Interactive learning from policydependent human feedback","volume-title":"International conference on machine learning","author":"MacGlashan","year":"2017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2011"},{"key":"ref11","article-title":"Guiding reinforcement learning exploration using natural language","author":"Harrison","year":"2017","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02448-8"},{"key":"ref13","first-page":"2024","article-title":"Large language model uncertainty measurement and calibration for medical diagnosis and treatment","author":"Savage","year":"2024","journal-title":"medRxiv"},{"key":"ref14","article-title":"Accelerating reinforcement learning of robotic manipulations via feedback from large language models","author":"Chu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Larger language models do in-context learning differently","author":"Wei","year":"2023","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"What learning algorithm is in-context learning? investigations with linear models","author":"Aky\u00fcrek","year":"2022","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10135-3"},{"key":"ref18","first-page":"8657","article-title":"Guiding pretraining in reinforcement learning with large language models","volume-title":"International Conference on Machine Learning","author":"Du","year":"2023"},{"key":"ref19","first-page":"3676","article-title":"Grounding large language models in interactive environments with online reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Carta","year":"2023"},{"key":"ref20","article-title":"Chatgpt is a knowledgeable but inexperienced solver: An investigation of commonsense problem in large language models","author":"Bian","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Learning to model the world with language","author":"Lin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01554"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1542\/peds.88.3.a78a"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.268"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-023-2689-5"},{"key":"ref26","article-title":"The National Artificial Intelligence Research and Development Strategic Plan:2023 Update","volume-title":"National Science and Technology Council (US), Select Committee on Artificial\u2026","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3390\/app10165574"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2017.2700395"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2262"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11485"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3006254"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.32473\/flairs.v34i1.128472"},{"key":"ref33","article-title":"Deep reinforcement learning from policy-dependent human feedback","author":"Arumugam","year":"2019","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.65109\/pajo3896"},{"key":"ref35","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"North American Chapter of the Association for Computational Linguistics","author":"Devlin","year":"2019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3497992"},{"key":"ref38","first-page":"1273","article-title":"Offline reinforcement learning as one big sequence modeling problem","volume":"34","author":"Janner","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref39","article-title":"Unleashing the power of pre-trained language models for offline reinforcement learning","author":"Shi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.704"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295309"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"ref43","article-title":"Understanding the capabilities, limitations, and societal impact of large language models","author":"Tamkin","year":"2021","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3461702.3462624"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99978-4_9"},{"key":"ref46","first-page":"215","article-title":"Ensemble learning in bayesian neural networks","volume":"168","author":"Barber","year":"1998","journal-title":"Nato ASI Series F Computer and Systems Sciences"},{"key":"ref47","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","volume":"30","author":"Lakshminarayanan","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.236"},{"key":"ref49","first-page":"1321","article-title":"On calibration of modern neural networks","volume-title":"International conference on machine learning","author":"Guo","year":"2017"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00407"},{"key":"ref51","article-title":"On the importance of uncertainty in decision-making with large language models","author":"Felicioni","year":"2024","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref53","article-title":"Policy shaping: Integrating human feedback with reinforcement learning","volume":"26","author":"Griffith","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref54","first-page":"3366","article-title":"Policy shaping with human teachers","author":"Cederborg","year":"2015","journal-title":"IJCAI"},{"key":"ref55","article-title":"Learning shaping strategies in human-in-the-loop interactive reinforcement learning","author":"Yu","year":"2018","journal-title":"arXiv preprint"},{"key":"ref56","volume-title":"Retrieval-augmented generation (rag)","year":"2023"}],"event":{"name":"2025 IEEE 7th International Conference on Trust, Privacy and Security in Intelligent Systems, and Applications (TPS-ISA)","location":"Pittsburgh, PA, USA","start":{"date-parts":[[2025,11,12]]},"end":{"date-parts":[[2025,11,14]]}},"container-title":["2025 IEEE 7th International Conference on Trust, Privacy and Security in Intelligent Systems, and Applications (TPS-ISA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11410113\/11410157\/11410280.pdf?arnumber=11410280","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T06:51:13Z","timestamp":1772607073000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11410280\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,12]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/tps-isa67132.2025.00045","relation":{},"subject":[],"published":{"date-parts":[[2025,11,12]]}}}