{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T21:14:57Z","timestamp":1777670097959,"version":"3.51.4"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"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":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/lra.2025.3528663","type":"journal-article","created":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T20:18:09Z","timestamp":1736972289000},"page":"2486-2493","source":"Crossref","is-referenced-by-count":8,"title":["PrefCLM: Enhancing Preference-Based Reinforcement Learning With Crowdsourced Large Language Models"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4323-8989","authenticated-orcid":false,"given":"Ruiqi","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Computer and Information Technology, SMART Laboratory, Purdue University, West Lafayette, IN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4478-9595","authenticated-orcid":false,"given":"Dezhong","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Computer and Information Technology, SMART Laboratory, Purdue University, West Lafayette, IN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8088-3636","authenticated-orcid":false,"given":"Ziqin","family":"Yuan","sequence":"additional","affiliation":[{"name":"Department of Computer and Information Technology, SMART Laboratory, Purdue University, West Lafayette, IN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3910-8890","authenticated-orcid":false,"given":"Ike","family":"Obi","sequence":"additional","affiliation":[{"name":"Department of Computer and Information Technology, SMART Laboratory, Purdue University, West Lafayette, IN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6458-4365","authenticated-orcid":false,"given":"Byung-Cheol","family":"Min","sequence":"additional","affiliation":[{"name":"Department of Computer and Information Technology, SMART Laboratory, Purdue University, West Lafayette, IN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"The ingredients of real world robotic reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu","year":"2019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3366414"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981616"},{"key":"ref4","first-page":"6768","article-title":"Inverse reward design","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hadfield-Menell","year":"2017"},{"key":"ref5","first-page":"4302","article-title":"Deep reinforcement learning from human preferences","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Christiano","year":"2017"},{"key":"ref6","first-page":"6152","article-title":"PEBBLE: Feedback-efficient interactive reinforcement learning via relabeling experience and unsupervised pre-training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lee","year":"2021"},{"key":"ref7","article-title":"B-pref: Benchmarking preference-based reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Lee","year":"2021"},{"key":"ref8","article-title":"SURF: Semi-supervised reward learning with data augmentation for feedback-efficient preference-based reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Park","year":"2021"},{"key":"ref9","first-page":"1484","article-title":"Sample-efficient preference-based reinforcement learning with dynamics aware rewards","volume-title":"Proc. 7th Annu. Conf. Robot Learn.","author":"Metcalf","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981076"},{"key":"ref11","first-page":"22270","article-title":"Meta-reward-net: Implicitly differentiable reward learning for preference-based reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu","year":"2022"},{"key":"ref12","article-title":"PrefMMT: Modeling human preferences in preference-based reinforcement learning with multimodal transformers","author":"Zhao","year":"2024"},{"key":"ref13","article-title":"Preference transformer: Modeling human preferences using transformers for RL","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Kim","year":"2022"},{"key":"ref14","article-title":"RL-VLM-F: Reinforcement learning from vision language foundation model feedback","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Wang","year":"2024"},{"key":"ref15","article-title":"Eureka: Human-level reward design via coding large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ma","year":"2024"},{"key":"ref16","article-title":"Text2Reward: Reward shaping with language models for reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xie","year":"2024"},{"key":"ref17","article-title":"MetaGPT: Meta programming for multi-agent collaborative framework","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Hong","year":"2023"},{"key":"ref18","article-title":"ChatEval: Towards better LLM-based evaluators through multi-agent debate","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Chan","year":"2023"},{"issue":"6","key":"ref19","first-page":"176","article-title":"The rise of crowdsourcing","volume":"14","author":"Howe","year":"2006","journal-title":"Wired Mag."},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019837"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.4018\/9781599048499.ch068"},{"key":"ref22","article-title":"Crowd-PrefRL: Preference-based reward learning from crowds","author":"Chhan","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341577"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"ref25","article-title":"Causal confusion and reward misidentification in preference-based reward learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tien","year":"2023"},{"key":"ref26","article-title":"Personalization in human-robot interaction through preference-based action representation learning","author":"Wang","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-021-00811-8"},{"key":"ref28","article-title":"Deepmind control suite","author":"Tassa","year":"2018"},{"key":"ref29","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Yu","year":"2020"},{"key":"ref30","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref31","article-title":"Are more LLM calls all you need? Towards scaling properties of compound AI systems","volume-title":"Proc. 38th Annu. Conf. Neural Inf. Process. Syst.","author":"Chen","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197411"},{"key":"ref33","article-title":"MediaPipe: A framework for building perception pipelines","author":"Lugaresi","year":"2019"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/10849592\/10840291.pdf?arnumber=10840291","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T05:22:23Z","timestamp":1738387343000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10840291\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":33,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3528663","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}