StateLinFormer: Stateful Training Enhancing Long-term Memory in Navigation

Read full text Summarise with VIRAT
Authors: Zhiyuan Chen, Yuxuan Zhong, Fan Wang, Bo Yu, Pengtao Shao, Shaoshan Liu, Ning Ding
Cited by: 0
References: 38

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Effective navigation intelligence relies on long-term memory to support both immediate generalization and sustained adaptation. However, existing approaches face a dilemma: modular systems rely on explicit mapping but lack flexibility, while Transformer-based end-to-end models are constrained by fixed context windows, limiting persistent memory across extended interactions. We introduce StateLinFormer, a linear-attention navigation model trained with a stateful memory mechanism that preserves recurrent memory states across consecutive training segments instead of reinitializing them at each batch boundary. This training paradigm effectively approximates learning on infinitely long sequences, enabling the model to achieve long-horizon memory retention. Experiments across both MAZE and ProcTHOR environments demonstrate that StateLinFormer significantly outperforms its stateless linear-attention counterpart and standard Transformer baselines with fixed context windows. Notably, as interaction length increases, persistent stateful training substantially improves context-dependent adaptation, suggesting an enhancement in the model's In-Context Learning (ICL) capabilities for navigation tasks.

Fields of Study & Subjects

Reinforcement Learning in Robotics Domain Adaptation and Few-Shot Learning AI-based Problem Solving and Planning

Publication details

Journal / source
arXiv (Cornell University)
Publication date
24 March 2026
Language
EN
Document type
Preprint