To cope with real-world dynamics, an intelligent system needs to incrementally acquire,
update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as …

Recently, foundation language models (LMs) have marked significant achievements in the
domains of natural language processing (NLP) and computer vision (CV). Unlike traditional …

In this paper, we characterize the behavior of canonical value-based deep reinforcement
learning (RL) approaches under varying degrees of non-stationarity. In particular, we …

The ability of continual learning systems to transfer knowledge from previously seen tasks in
order to maximize performance on new tasks is a significant challenge for the field, limiting …

The training of sparse neural networks is becoming an increasingly important tool for
reducing the computational footprint of models at training and evaluation, as well enabling …

Continual learning is a subfield of machine learning, which aims to allow machine learning
models to continuously learn on new data, by accumulating knowledge without forgetting …

Progress in continual reinforcement learning has been limited due to several barriers to
entry: missing code, high compute requirements, and a lack of suitable benchmarks. In this …

Continual learning is the problem of learning from a nonstationary stream of data, a
fundamental issue for sustainable and efficient training of deep neural networks over time …

The ability to continuously acquire new knowledge and skills is crucial for autonomous
agents. Existing methods are typically based on either fixed-size models that struggle to …

Continual learning (CL) is under-explored in the video domain. The few existing works
contain splits with imbalanced class distributions over the tasks, or study the problem in …