{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:27:24Z","timestamp":1780763244501,"version":"3.54.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650538","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":6,"title":["Real-time Integration of Fine-tuned Large Language Model for Improved Decision-Making in Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Xiancai","family":"Xiang","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Xue","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Lei","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Yue","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke","family":"Lu","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.03.003"},{"key":"ref2","author":"Du","year":"2023","journal-title":"Guiding pretraining in reinforcement learning with large language models"},{"key":"ref3","author":"Wu","year":"2023","journal-title":"SPRING: GPT-4 Out-performs RL Algorithms by Studying Papers and Reasoning"},{"key":"ref4","article-title":"Can ChatGPT Enable ITS?","author":"Villarreal","year":"2023","journal-title":"The Case of Mixed Traffic Control via Reinforcement Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10299-x"},{"key":"ref6","first-page":"15931","article-title":"Learning to Utilize Shaping Rewards: A New Approach of Reward Shaping","volume":"33","author":"Hu","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","first-page":"5829","article-title":"Exploration-Guided Reward Shaping for Reinforcement Learning under Sparse Rewards","volume":"35","author":"Devidze","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103500"},{"key":"ref9","article-title":"Multi-Agent Generative Adversarial Imitation Learning","volume":"31","author":"Song","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","first-page":"15737","article-title":"Error Bounds of Imitating Policies and Environments","volume":"33","author":"Xu","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3061397"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103191"},{"key":"ref13","author":"Devlin","year":"2019","journal-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding"},{"key":"ref14","first-page":"1877","article-title":"Language Models are Few-Shot Learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","year":"2023","journal-title":"GPT-4 Technical Report"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1177\/1729881419851402"},{"key":"ref17","author":"Yang","year":"2023","journal-title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3125739.3132579"},{"key":"ref19","author":"Chen","year":"2023","journal-title":"AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkers"},{"key":"ref20","author":"Qiu","year":"2023","journal-title":"Embodied Executable Policy Learning with Language-based Scene Summarization"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"ref22","author":"Zhao","year":"2023","journal-title":"Large Language Models as Commonsense Knowledge for Large-Scale Task Planning"},{"key":"ref23","author":"Guan","year":"2023","journal-title":"Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning"},{"key":"ref24","author":"Mandi","year":"2023","journal-title":"RoCo: Dialectic Multi-Robot Collaboration with Large Language Models"},{"key":"ref25","author":"Qiu","year":"2023","journal-title":"Embodied Executable Policy Learning with Language-based Scene Summarization"},{"key":"ref26","article-title":"Can Large Language Models Play Text Games Well?","author":"Tsai","year":"2023","journal-title":"Current State-of-the-Art and Open Questions"},{"key":"ref27","author":"Wang","year":"2023","journal-title":"Voyager: An Open-Ended Embodied Agent with Large Language Models"},{"key":"ref28","author":"Hu","year":"2023","journal-title":"Enabling Intelligent Interactions between an Agent and an LLM: A Reinforcement Learning Approach"},{"key":"ref29","article-title":"Glm-130b: An open bilingual pre-trained model","author":"Zeng","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.2514\/6.2004-4923"},{"key":"ref32","article-title":"Light Aircraft Game: A lightweight, scalable, gym-wrapped aircraft competitive environment with baseline reinforcement learning algorithms","author":"Liu","year":"2022","journal-title":"GitHub"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","location":"Yokohama, Japan","start":{"date-parts":[[2024,6,30]]},"end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10650538.pdf?arnumber=10650538","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T05:28:04Z","timestamp":1725946084000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650538\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650538","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}