{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T14:09:45Z","timestamp":1768572585058,"version":"3.49.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T00:00:00Z","timestamp":1765670400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T00:00:00Z","timestamp":1765670400000},"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":[[2025,12,14]]},"DOI":"10.1109\/icpads67057.2025.11323099","type":"proceedings-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T20:36:54Z","timestamp":1768423014000},"page":"1-9","source":"Crossref","is-referenced-by-count":0,"title":["DRL-VLA: An Optimization Method for VLA Model Based on Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Mengkun","family":"Zhang","sequence":"first","affiliation":[{"name":"China Unicom (Heilongjiang) Industrial Internet Co., Ltd.,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengfei","family":"Gao","sequence":"additional","affiliation":[{"name":"China Unicom (Heilongjiang) Industrial Internet Co., Ltd.,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinuo","family":"Sheng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Shenzhen,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ran","family":"Li","sequence":"additional","affiliation":[{"name":"China Unicom (Heilongjiang) Industrial Internet Co., Ltd.,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingliang","family":"An","sequence":"additional","affiliation":[{"name":"China Unicom (Heilongjiang) Industrial Internet Co., Ltd.,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenxin","family":"Wang","sequence":"additional","affiliation":[{"name":"China Unicom (Heilongjiang) Industrial Internet Co., Ltd.,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802201"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3136814"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802225"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3061377"},{"key":"ref5","author":"Yenamandra","year":"2023","journal-title":"Homerobot: Open-vocabulary mobile manipulation"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0171"},{"key":"ref7","first-page":"284","article-title":"Gnfactor: Multi-task real robot learning with generalizable neural feature fields","volume-title":"Conference on robot learning","author":"Ze","year":"2023"},{"key":"ref8","author":"Kim","year":"2024","journal-title":"Openvla: An opensource vision-language-action model"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01710"},{"key":"ref10","author":"Gu","year":"2023","journal-title":"Rt-trajectory: Robotic task generalization via hindsight trajectory sketches"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00167"},{"key":"ref12","author":"Shi","year":"2023","journal-title":"Robocook: Long-horizon elasto-plastic object manipulation with diverse tools"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref14","author":"Fu","year":"2024","journal-title":"Mobile aloha: Learning bimanual mobile manipulation with low-cost whole-body teleoperation"},{"key":"ref15","article-title":"Robot learning in homes: Improving generalization and reducing dataset bias","volume":"31","author":"Gupta","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref16","author":"Mendonca","year":"2024","journal-title":"Continuously improving mobile manipulation with autonomous real-world rl"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/iros60139.2025.11246780"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.091"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01717"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3544909"},{"key":"ref21","author":"Liu","year":"2024","journal-title":"Rdt-1b: a diffusion foundation model for bimanual manipulation"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.010"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812312"},{"key":"ref24","author":"Luo","year":"2023","journal-title":"Rlif: Interactive imitation learning as reinforcement learning"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794102"},{"key":"ref26","author":"Zhuang","year":"2023","journal-title":"Robot parkour learning"},{"key":"ref27","author":"Mark","year":"2024","journal-title":"Policy agnostic rl: Offline rl and online rl fine-tuning of any class and backbone"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273590"},{"key":"ref29","volume-title":"Conq hose manipulation dataset, v1.15.0","author":"Mitrano","year":"2024"},{"key":"ref30","author":"Shafiullah","year":"2023","journal-title":"On bringing robots home"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241276017"},{"key":"ref32","author":"Wang","year":"2023","journal-title":"Mimicplay: Long-horizon imitation learning by watching human play"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10611293"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10139-z"},{"key":"ref35","article-title":"Vima: General robot manipulation with multimodal prompts","volume-title":"Fortieth International Conference on Machine Learning","author":"Jiang","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01537"},{"key":"ref37","article-title":"Plex: Making the most of the available data for robotic manipulation pretraining","author":"Thomas","year":"2023","journal-title":"CoRL"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01550"},{"key":"ref39","author":"Liu","year":"2023","journal-title":"Libero: Benchmarking knowledge transfer for lifelong robot learning"}],"event":{"name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","location":"Hefei, China","start":{"date-parts":[[2025,12,14]]},"end":{"date-parts":[[2025,12,18]]}},"container-title":["2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11322805\/11322871\/11323099.pdf?arnumber=11323099","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T07:26:02Z","timestamp":1768461962000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11323099\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icpads67057.2025.11323099","relation":{},"subject":[],"published":{"date-parts":[[2025,12,14]]}}}