arXiv AI
Permanent and Transient Representations for Continual Reinforcement Learning
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 8
To Retain or to Adapt? Generalizing Continual Learning
arXiv:2607. 05609v1 Announce Type: cross Abstract: The Continual Learning (CL) literature has long been driven by the goal of mitigating catastrophic forgetting.
arXiv Machine Learning
Jul 7
RL Forgets! Towards Continual Policy Optimization
arXiv:2607. 04364v1 Announce Type: new Abstract: Continual post-training is becoming a central paradigm for adapting vision-language models to evolving tasks.
arXiv AI
Jun 3
Re-Evaluating Continual Learning with Few-Shot Adaptation
arXiv:2606. 03843v1 Announce Type: cross Abstract: Continual learning methods aim to maximize the stability and plasticity of machine learning models that are trained on a sequence of tasks.
arXiv AI
Oct 5
How to Find and Reuse Policies for Continuous Adaptation in Lifelong Reinforcement Learning
The paper introduces Adaptive Mask Selection and Composition (AMSC), a method that estimates task similarity using non‑parametric Wasserstein embeddings from state‑action‑reward samples. AMSC selects and weights previously learned policies based on z‑score‑normalized sparsemax similarity scores, forming a prior for new tasks. Experiments on CT‑graph, MiniGrid, and Continual World show that AMSC improves mean performance and forward transfer while avoiding forgetting, highlighting the importance of selecting relevant prior knowledge and its layer‑specific composition.
arXiv AI
Oct 31
Episodic looking - using reinforcement learning to bias perception enhances few-shot and continual learning with protection from forgetting
The paper addresses the conflict between generalization and continuous adaptation in few‑shot and continual learning. It proposes a Complementary Learning System (CLS) that separates a fast Short‑Term Memory (STM) for memorizing recent inputs from a slow Long‑Term Memory (LTM) that provides robust, generalized perceptions. Experiments on image classification show the CLS model resists forgetting in domain‑incremental continual learning and outperforms other continual learners in few‑shot settings, though overall accuracy is slightly lower than some existing methods.
arXiv Machine Learning
4d ago
Before We Adapt: The Zero-Shot Generalization Bottleneck in Continual World Models
The paper investigates how model-based reinforcement learning can support continual learning by reusing prior knowledge. It introduces a contextual Markov decision process that separates behavioral and physical context, and studies zero‑shot reuse in FourRooms tasks using Dyna‑Q and TD‑MPC. The experiments show that zero‑shot reuse degrades under physical context changes and that this degradation is strongly tied to the observation representation, highlighting representation generalization as a key bottleneck.