arXiv AI October 5, 2026 By Saptarshi Nath, Inish M. D'Souza, Antonio Carta, Soheil Kolouri, Andrea Soltoggio

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jun 10

Beyond Single-Model Optimization: Preserving Plasticity in Continual Reinforcement Learning

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.

By Lute Lillo, Nick Cheney

agents diffusion reinforcement-learning

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.

By Mao-Lin Luo, Zhe-Xu Wang, Zi-Hao Zhou, Bo Ye, Jian Zhao, Min-Ling Zhang, Tong Wei

llms reinforcement-learning fine-tuning multimodal benchmarks

arXiv Machine Learning

Jul 8

Fine-Tuning Regimes Define Distinct Continual Learning Problems

arXiv:2604. 21927v3 Announce Type: replace Abstract: Continual learning (CL) studies how models acquire tasks sequentially while retaining previously learned knowledge.

By Paul-Tiberiu Iordache, Elena Burceanu

fine-tuning benchmarks

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.

By Giulia Lanzillotta, Mandana Samiei, Doina Precup, Razvan Pascanu, Claire Vernade

computer-vision reinforcement-learning benchmarks safety

arXiv AI

Jun 30

Neural Subspace Reallocation: Continual Learning as Retrieval-Based Subspace Memory Management

arXiv:2606. 30067v1 Announce Type: cross Abstract: We introduce Neural Subspace Reallocation (NSR), which reframes continual learning as memory management over parameter subspaces.

By Byeong Hoon Yoon

rag fine-tuning efficiency benchmarks

arXiv Machine Learning

Sep 23

ELEMENT: Episodic and Lifelong Exploration via Maximum Entropy

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.

By Hongming Li, Zhao Yang, Xiaoxuan Liang, Shujian Yu, Jose C. Principe

agents reinforcement-learning benchmarks

One email a morning, machine-written

Related stories

Beyond Single-Model Optimization: Preserving Plasticity in Continual Reinforcement Learning

RL Forgets! Towards Continual Policy Optimization

Fine-Tuning Regimes Define Distinct Continual Learning Problems

To Retain or to Adapt? Generalizing Continual Learning

Neural Subspace Reallocation: Continual Learning as Retrieval-Based Subspace Memory Management

ELEMENT: Episodic and Lifelong Exploration via Maximum Entropy