{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T11:10:55Z","timestamp":1772277055427,"version":"3.50.1"},"reference-count":15,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T00:00:00Z","timestamp":1768089600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T00:00:00Z","timestamp":1768089600000},"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":[[2026,1,11]]},"DOI":"10.1109\/sii64115.2026.11404492","type":"proceedings-article","created":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T20:47:13Z","timestamp":1772225233000},"page":"722-728","source":"Crossref","is-referenced-by-count":0,"title":["Rewarding Change Beyond State: Directional VLM Rewards for Sample-Efficient Robot Reinforcement Learning\n                    <sup>*<\/sup>"],"prefix":"10.1109","author":[{"given":"Linus","family":"Lundgren","sequence":"first","affiliation":[{"name":"Chalmers University of Technology,Faculty of Computer Science and Engineering,Gothenburg,Sweden,SE-412 96"}]},{"given":"Wenhao","family":"Lu","sequence":"additional","affiliation":[{"name":"Chalmers University of Technology,Faculty of Electrical Engineering,Gothenburg,Sweden,SE-412 96"}]},{"given":"Zhitao","family":"Liang","sequence":"additional","affiliation":[{"name":"Chalmers University of Technology,Faculty of Electrical Engineering,Gothenburg,Sweden,SE-412 96"}]},{"given":"Ze","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chalmers University of Technology,Faculty of Computer Science and Engineering,Gothenburg,Sweden,SE-412 96"}]},{"given":"Karinne","family":"Ramirez-Amaro","sequence":"additional","affiliation":[{"name":"Chalmers University of Technology,Faculty of Electrical Engineering,Gothenburg,Sweden,SE-412 96"}]},{"given":"Emmanuel","family":"Dean","sequence":"additional","affiliation":[{"name":"Chalmers University of Technology,Faculty of Electrical Engineering,Gothenburg,Sweden,SE-412 96"}]}],"member":"263","reference":[{"issue":"30","key":"ref1","first-page":"1","article-title":"A review of robot learning for manipulation: Challenges, representations, and algorithms","volume":"22","author":"Kroemer","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"ref2","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning (ICML)","author":"Radford"},{"key":"ref3","article-title":"Vision-language models as a source of rewards","volume-title":"Second Agent Learning in Open-Endedness Workshop, NeurIPS","author":"Baumli"},{"key":"ref4","article-title":"Vision-language models are zero-shot reward models for reinforcement learning","volume-title":"International Conference on Learning Representations (ICLR)","author":"Rocamonde"},{"key":"ref5","article-title":"VLM-RL: A unified vision language models and reinforcement learning framework for safe autonomous driving","author":"Huang","year":"2024"},{"key":"ref6","first-page":"14 256","article-title":"FuRL: Visual-language models as fuzzy rewards for reinforcement learning","volume-title":"International Conference on Machine Learning (ICML)","author":"Fu"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2025\/1181"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.111004"},{"key":"ref9","first-page":"48 203","article-title":"TACO: Temporal latent action-driven contrastive loss for visual reinforcement learning","volume":"36","author":"Zheng","year":"2023","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref10","article-title":"Internal model from observations for reward shaping","volume-title":"Adaptive Learning Agents Workshop, Federated AI Meeting (FAIM)","author":"Kimura"},{"key":"ref11","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref12","article-title":"The dark side of rich rewards: Understanding and mitigating noise in VLM rewards","author":"Huang","year":"2024"},{"key":"ref13","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International Conference on Machine Learning (ICML)","author":"Haarnoja"},{"key":"ref14","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Conference on Robot Learning (CoRL)","author":"Yu"},{"key":"ref15","first-page":"23 301","article-title":"Liv: Language-image representations and rewards for robotic control","volume-title":"International Conference on Machine Learning","author":"Ma"}],"event":{"name":"2026 IEEE\/SICE International Symposium on System Integration (SII)","location":"Cancun, Mexico","start":{"date-parts":[[2026,1,11]]},"end":{"date-parts":[[2026,1,14]]}},"container-title":["2026 IEEE\/SICE International Symposium on System Integration (SII)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11404435\/11404394\/11404492.pdf?arnumber=11404492","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T06:58:19Z","timestamp":1772261899000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11404492\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,11]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/sii64115.2026.11404492","relation":{},"subject":[],"published":{"date-parts":[[2026,1,11]]}}}