← 研踪 PaperTrailarXiv:2611.19901 · v1
Remember, Replay, Adapt: Learning from Past Experience in Online Vision-and-Language Navigation
首次提交 2026-11-15 17:30
版本更新 2026-11-15 17:30
雷达观测 2026-11-17 12:06
摘要
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%.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-15 17:30 · 最新观测版本
Remember, Replay, Adapt: Learning from Past Experience in Online Vision-and-Language Navigation
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%.
查看此版本解读 →查看此版本原文 ↗