In this article, we aim to provide a literature review of different formulations and approaches
to continual reinforcement learning (RL), also known as lifelong or non-stationary RL. We …

Artificial neural networks (ANNs) have emerged as an essential tool in machine learning,
achieving remarkable success across diverse domains, including image and speech …

While deep reinforcement learning (RL) has fueled multiple high-profile successes in
machine learning, it is held back from more widespread adoption by its often poor data …

Structured state space sequence (S4) models have recently achieved state-of-the-art
performance on long-range sequence modeling tasks. These models also have fast …

Modern machine learning requires system designers to specify aspects of the learning
pipeline, such as losses, architectures, and optimizers. Meta-learning, or learning-to-learn …

Genetic algorithms constitute a family of black-box optimization algorithms, which take
inspiration from the principles of biological evolution. While they provide a general-purpose …

Optimizing functions without access to gradients is the remit of black-box methods such as
evolution strategies. While highly general, their learning dynamics are often times heuristic …

Intelligent agents should have the ability to leverage knowledge from previously learned
tasks in order to learn new ones quickly and efficiently. Meta-learning approaches have …

A challenging problem in many modern machine learning tasks is to process weight-space
features, ie, to transform or extract information from the weights and gradients of a neural …

Intelligent agents should have the ability to leverage knowledge from previously learned
tasks in order to learn new ones quickly and efficiently. Meta-learning approaches have …