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 …

Generalization and sample efficiency have been long-standing issues concerning
reinforcement learning, and thus the field of Offline Meta-Reinforcement Learning (OMRL) …

Offline meta-reinforcement learning (OMRL) utilizes pre-collected offline datasets to
enhance the agent's generalization ability on unseen tasks. However, the context shift …

Deep reinforcement learning (DRL) has led to a wide range of advances in sequential
decision-making tasks. However, the complexity of neural network policies makes it difficult …

While Reinforcement Learning (RL) has made great strides towards solving increasingly
complicated problems, many algorithms are still brittle to even slight environmental changes …

Multi-agent reinforcement learning is promising for real-world applications as it encourages
agents to perceive and interact with their surrounding environment autonomously. However …

Standard reinforcement learning (RL) agents never intelligently explore like a human (ie by
taking into account complex domain priors and previous explorations). Even the most basic …

In meta reinforcement learning (meta RL), an agent seeks a Bayes-optimal policy–the
optimal policy when facing an unknown task that is sampled from some known task …

Adapting to the changes in transition dynamics is essential in robotic applications. By
learning a conditional policy with a compact context, context-aware meta-reinforcement …