{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T10:59:58Z","timestamp":1766055598651,"version":"3.48.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11247576","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"746-753","source":"Crossref","is-referenced-by-count":0,"title":["Application of LLM Guided Reinforcement Learning in Formation Control with Collision Avoidance"],"prefix":"10.1109","author":[{"given":"Chenhao","family":"Yao","sequence":"first","affiliation":[{"name":"Shenzhen Technology University,School of Sino-German College of Intelligent Manufacturing,Shenzhen,China,518118"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zike","family":"Yuan","sequence":"additional","affiliation":[{"name":"Shenzhen Technology University,School of Sino-German College of Intelligent Manufacturing,Shenzhen,China,518118"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoxu","family":"Liu","sequence":"additional","affiliation":[{"name":"Shenzhen Technology University,School of Sino-German College of Intelligent Manufacturing,Shenzhen,China,518118"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chi","family":"Zhu","sequence":"additional","affiliation":[{"name":"Shenzhen Technology University,School of Sino-German College of Intelligent Manufacturing,Shenzhen,China,518118"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/ICRA.2011.5980408"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/TCSII.2021.3112787"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.12794\/metadc1505267"},{"key":"ref4","first-page":"1407","article-title":"Impala: Scalable distributed deep-rl with importance weighted actor-learner architectures","volume-title":"International conference on machine learning","author":"Espeholt"},{"issue":"178","key":"ref5","first-page":"1","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"Journal of Machine Learning Research"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1038\/s41586-019-1724-z"},{"year":"2019","author":"Berner","article-title":"Dota 2 with large scale deep reinforcement learning","key":"ref7"},{"key":"ref8","first-page":"24 611","article-title":"The surprising effectiveness of ppo in cooperative multi-agent games","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Yu","year":"2022"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/TNNLS.2020.3004893"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/ICRA46639.2022.9812263"},{"year":"2022","author":"Ahn","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","key":"ref11"},{"volume-title":"Forty-first International Conference on Machine Learning","author":"Wang","article-title":"Executable code actions elicit better LLM agents","key":"ref12"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/LRA.2024.3511402"},{"year":"2023","author":"Xie","article-title":"Text2Reward: Reward Shaping with Language Models for Reinforcement Learning","key":"ref14"},{"year":"2023","author":"Ma","article-title":"Eureka: Human-level reward design via coding large language models","key":"ref15"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/TCYB.2021.3063481"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/TRO.2023.3236945"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/TII.2020.3004343"},{"volume-title":"Markov decision processes: discrete stochastic dynamic programming","year":"2014","author":"Puterman","key":"ref19"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/ICRA46639.2022.9812050"},{"year":"2015","author":"Schulman","article-title":"High-dimensional continuous control using generalized advantage estimation","key":"ref21"},{"year":"2016","author":"Mnih","article-title":"Asynchronous Methods for Deep Reinforcement Learning","key":"ref22"},{"year":"2024","author":"Yang","article-title":"Qwen2.5 Technical Report","key":"ref23"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/ICRA.2017.7989037"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.15607\/RSS.2024.XX.094"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11247576.pdf?arnumber=11247576","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T10:55:18Z","timestamp":1766055318000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247576\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247576","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}