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 …

This paper serves to introduce the reader to the field of multi-agent reinforcement learning
(MARL) and its intersection with methods from the study of causality. We highlight key …

As humans, our goals and our environment are persistently changing throughout our lifetime
based on our experiences, actions, and internal and external drives. In contrast, typical …

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 …

Reinforcement learning is a promising paradigm for solving sequential decision-making
problems, but low data efficiency and weak generalization across tasks are bottlenecks in …

Test-time adaptation (TTA) aims to adapt a trained classifier using online unlabeled test data
only, without any information related to the training procedure. Most existing TTA methods …

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

Meta-reinforcement learning (meta-RL) aims to learn from multiple training tasks the ability
to adapt efficiently to unseen test tasks. Despite the success, existing meta-RL algorithms …

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 …

Recent offline meta-reinforcement learning (meta-RL) methods typically utilize task-
dependent behavior policies (eg, training RL agents on each individual task) to collect a …