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 …

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 …

A major goal of artificial intelligence (AI) is to create an agent capable of acquiring a general
understanding of the world. Such an agent would require the ability to continually …

We propose BOSS, an approach that automatically learns to solve new long-horizon,
complex, and meaningful tasks by growing a learned skill library with minimal supervision …

Decision Transformers (DT) have demonstrated strong performances in offline reinforcement
learning settings, but quickly adapting to unseen novel tasks remains challenging. To …

In the field of unsupervised skill discovery (USD), a major challenge is limited exploration,
primarily due to substantial penalties when skills deviate from their initial trajectories. To …

Identifying statistical regularities in solutions to some tasks in multi-task reinforcement
learning can accelerate the learning of new tasks. Skill learning offers one way of identifying …

Reinforcement Learning (RL), bolstered by the expressive capabilities of Deep Neural
Networks (DNNs) for function approximation, has demonstrated considerable success in …

Pre-training robots with a rich set of skills can substantially accelerate the learning of
downstream tasks. Prior works have defined pre-training tasks via natural language …

Offline reinforcement learning (RL) enables the agent to effectively learn from logged data,
which significantly extends the applicability of RL algorithms in real-world scenarios where …