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 …

A number of decarbonization scenarios for the energy sector are built on simultaneous
electrification of energy demand, and decarbonization of electricity generation through …

Multi-task learning (MTL) is a subfield of machine learning in which multiple tasks are
simultaneously learned by a shared model. Such approaches offer advantages like …

Multi-Task Learning (MTL) is a learning paradigm in machine learning and its aim is to
leverage useful information contained in multiple related tasks to help improve the …

Offline reinforcement learning (RL) algorithms have shown promising results in domains
where abundant pre-collected data is available. However, prior methods focus on solving …

Generalization across environments is critical to the successful application of reinforcement
learning (RL) algorithms to real-world challenges. In this work we propose a method for …

We posit that a reinforcement learning (RL) agent will perform better when it uses
representations that are better at predicting the future, particularly in terms of few-shot …

The purpose of multi-task reinforcement learning (MTRL) is to train a single policy that can
be applied to a set of different tasks. Sharing parameters allows us to take advantage of the …

We study the problem of representational transfer in RL, where an agent first pretrains in a
number of\emph {source tasks} to discover a shared representation, which is subsequently …

With the emergence of varied visual navigation tasks (eg, image-/object-/audio-goal and
vision-language navigation) that specify the target in different ways, the community has …