cs.CVNov 15, 2026

Remember, Replay, Adapt: Learning from Past Experience in Online Vision-and-Language Navigation

Authors: Chenhao Ding, Jizhou Han, Lixin Xiu, Muyao Wang, Songlin Dong, Hideki Nakayama

Organizations: The University of Tokyo Tokyo, Japan · Xi’an Jiaotong University Xi’an, China · Shenzhen University of Advanced Technology Shenzhen, China

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%.

Figures & tables

Explore similar work

CardsList
  1. Joint On-and-Off Policy Learning for Vision-and-Language Navigation

    Jul 15, 2026Qingrong He, Lin Zhao, Kevin Zheng +1Vision-Language NavigationInteractive Imitation Learning

  2. MemoryVLN: From Ego-Aware Memory Representation to Cross-Context Memory Reuse in Vision-Language Navigation

    Oct 13, 2026Xueyao Wei, Yifei Wang, Delun Li +4Vision-Language NavigationMemory-Augmented VLMs

  3. Trajectory-Diversity-Driven Robust Vision-and-Language Navigation

    Mar 16, 2026Jiangyang Li, Cong Wan, SongLin Dong +4Vision-Language Navigation