arXiv · 2611.19901
Remember, Replay, Adapt: Learning from Past Experience in Online Vision-and-Language Navigation
Abstract
Existing feedback-based methods for online vision-and-language navigation (VLN) primarily learn from current episode outcomes, leaving previously acquired feedback underutilized. Inspired by human episodic memory, we propose R2A, an online VLN adaptation framework that continually reuses successful and failed navigation experiences for policy learning. Specifically, Success-Failure Memory (SFM) retains successful and failed navigation episodes with acquired feedback and retrieves task-relevant experiences based on incoming instructions, enabling historical feedback to guide subsequent navigation. Prior-Anchored Adaptation (PAA) learns from these experiences by reinforcing successful trajectories and suppressing failed ones relative to a frozen pretrained policy, while regularizing behavioral drift. Together, these modules enable continual feedback reuse and stable policy adaptation without source-domain data or expert supervision. Extensive experiments across three benchmarks, REVERIE, R2R, and R2R-CE, and five navigation backbones demonstrate consistent performance gains. On the REVERIE validation unseen split, R2A improves DUET's SR from 46.98% to 69.84% and SPL from 33.73% to 50.98%.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Chenhao Ding, Jizhou Han, Lixin Xiu, Muyao Wang, Songlin Dong, Hideki Nakayama. 2026-11-15. Remember, Replay, Adapt: Learning from Past Experience in Online Vision-and-Language Navigation. https://searcharxiv.com/abs/2611.19901
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.