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:2604. 15414v2 Announce Type: replace-cross Abstract: Continual reinforcement learning must balance retention with adaptation, yet many methods still rely on \emph{single-model preservation}, committing to one evolving policy as the main reusable solution across tasks.
arXiv:2607. 04364v1 Announce Type: new Abstract: Continual post-training is becoming a central paradigm for adapting vision-language models to evolving tasks.
arXiv:2604. 21927v3 Announce Type: replace Abstract: Continual learning (CL) studies how models acquire tasks sequentially while retaining previously learned knowledge.
arXiv:2607. 05609v1 Announce Type: cross Abstract: The Continual Learning (CL) literature has long been driven by the goal of mitigating catastrophic forgetting.
arXiv:2606. 30067v1 Announce Type: cross Abstract: We introduce Neural Subspace Reallocation (NSR), which reframes continual learning as memory management over parameter subspaces.
The paper introduces ELEMENT, a framework that combines episodic and lifelong entropy maximization to drive reward-free exploration in reinforcement learning. It addresses two key limitations of existing entropy-based methods: the vanishing intrinsic reward after a state is visited and the computational cost of estimating entropy over large datasets. ELEMENT achieves this by deriving an average episodic state entropy reward and employing a k‑NN graph‑based estimator for lifelong entropy, leading to superior state coverage and unsupervised pre‑training performance compared to current baselines.
arXiv:2607. 07847v1 Announce Type: new Abstract: As large language models (LLMs) become increasingly capable, the next question is how can we enable models to continually learn?
arXiv:2606. 16256v1 Announce Type: cross Abstract: Continual learning for pre-trained vision-language models requires balancing three competing objectives: retaining pre-trained knowledge, preserving knowledge from a sequence of learned tasks, and maintaining the plasticity to acquire new knowledge.
arXiv:2608. 11690v1 Announce Type: new Abstract: Continual learning must absorb new tasks without erasing old ones, and replay---mixing a small buffer of past examples into current training---is among the most effective remedies for catastrophic forgetting.
arXiv:2506. 10355v2 Announce Type: replace Abstract: Many real-world applications collect data in a streaming environment, where learning tasks are encountered sequentially.
arXiv:2510. 18874v3 Announce Type: replace Abstract: Adapting language models (LMs) to new tasks via post-training carries the risk of degrading existing capabilities -- a phenomenon classically known as catastrophic forgetting.
The paper introduces a compositional continual learning benchmark for world models in robot manipulation, designed to isolate knowledge reuse from learning speed and capacity. Tasks are curated to combine previously seen action and perception components, allowing analysis of how different modalities affect reuse. Experiments show that modular world models better balance reuse and forgetting than conventional methods, yet none fully solve the challenge, highlighting the need for models explicitly built to reuse knowledge without forgetting.