StateLinFormer: Stateful Training Enhancing Long-term Memory in Navigation
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Time-Efficient Reinforcement Learning with Stochastic Stateful Policies
Stateful policies play an important role in reinforcement learning, such as handling partially observable environments, enhancing robustness, or imposing an inductive bias directly into the policy structure. The conventi…
continuous-controlContinuous ControlImitation LearningInductive Bias+2Effect of Architectures and Training Methods on the Performance of Learned Video Frame Prediction
We analyze the performance of feedforward vs. recurrent neural network (RNN) architectures and associated training methods for learned frame prediction. To this effect, we trained a residual fully convolutional neural ne…
PredictionMini-Batch Learning Strategies for modeling long term temporal dependencies: A study in environmental applications
In many environmental applications, recurrent neural networks (RNNs) are often used to model physical variables with long temporal dependencies. However, due to mini-batch training, temporal relationships between trainin…
Exploiting the ConvLSTM: Human Action Recognition using Raw Depth Video-Based Recurrent Neural Networks
As in many other different fields, deep learning has become the main approach in most computer vision applications, such as scene understanding, object recognition, computer-human interaction or human action recognition …
Action RecognitionObject RecognitionScene UnderstandingTemporal Action LocalizationTVCACHE: A Stateful Tool-Value Cache for Post-Training LLM Agents
In RL post-training of LLM agents, calls to external tools take several seconds or even minutes, leaving allocated GPUs idle and inflating post-training time and cost. While many tool invocations repeat across parallel r…