Continual learning (CL) is a particular machine learning paradigm where the data
distribution and learning objective change through time, or where all the training data and …

In recent years, deep artificial neural networks (including recurrent ones) have won
numerous contests in pattern recognition and machine learning. This historical survey …

Reinforcement learning is a learning paradigm for solving sequential decision-making
problems. Recent years have witnessed remarkable progress in reinforcement learning …

The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent
years. Contrary to conventional approaches to AI where tasks are solved from scratch using …

Lack of performance when it comes to continual learning over non-stationary distributions of
data remains a major challenge in scaling neural network learning to more human realistic …

In a standard view of the reinforcement learning problem, an agent's goal is to efficiently
identify a policy that maximizes long-term reward. However, this perspective is based on a …

We introduce a conceptually simple and scalable framework for continual learning domains
where tasks are learned sequentially. Our method is constant in the number of parameters …

One major obstacle towards AI is the poor ability of models to solve new problems quicker,
and without forgetting previously acquired knowledge. To better understand this issue, we …

For artificial general intelligence (AGI) it would be efficient if multiple users trained the same
giant neural network, permitting parameter reuse, without catastrophic forgetting. PathNet is …

Value functions are a core component of reinforcement learning. The main idea is to to
construct a single function approximator V (s; theta) that estimates the long-term reward from …