持续视觉与语言导航
Continual Vision-and-Language Navigation
AI总结：
针对视觉与语言导航智能体在持续新环境中的适应问题，提出持续视觉与语言导航（CVLN）范式及两种设置，并设计PerpR与ESR两种重放基线，通过高效利用重放内存实现更优的持续学习性能。
摘要：
开发视觉与语言导航（VLN）智能体通常采用“一次训练一次部署”策略，这不切实际，因为部署的智能体会持续遇到新环境。为此，我们提出持续视觉与语言导航（CVLN）范式，智能体在多个场景域中增量学习与适应。CVLN包含两种设置：用于指令遵循的基于初始指令的CVLN，以及用于对话引导导航的基于对话的CVLN。我们还引入了两个简单有效的顺序决策基线：重放困难片段的Perplexity Replay（PerpR），以及在训练期间存储并重访动作logits的Episodic Self-Replay（ESR）。实验表明，现有持续学习方法在CVLN上表现不佳，而PerpR和ESR通过高效利用重放内存取得了更好性能。
英文摘要：
Developing Vision-and-Language Navigation (VLN) agents typically assumes a \textit{train-once-deploy-once} strategy, which is unrealistic as deployed agents continually encounter novel environments. To address this, we propose the Continual Vision-and-Language Navigation (CVLN) paradigm, where agents learn and adapt incrementally across multiple \textit{scene domains}. CVLN includes two setups: Initial-instruction based CVLN for instruction-following, and Dialogue-based CVLN for dialogue-guided navigation. We also introduce two simple yet effective baselines for sequential decision-making: Perplexity Replay (PerpR), which replays difficult episodes, and Episodic Self-Replay (ESR), which stores and revisits action logits during training. Experiments show that existing continual learning methods fall short for CVLN, while PerpR and ESR achieve better performance by efficiently utilizing replay memory.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
