In this tutorial article, we aim to provide the reader with the conceptual tools needed to get
started on research on offline reinforcement learning algorithms: reinforcement learning …

Intelligent agents rely heavily on prior experience when learning a new task, yet most
modern reinforcement learning (RL) approaches learn every task from scratch. One …

Navigating through unstructured environments is a basic capability of intelligent creatures,
and thus is of fundamental interest in the study and development of artificial intelligence …

Navigation is a rich and well-grounded problem domain that drives progress in many
different areas of research: perception, planning, memory, exploration, and optimisation in …

With the fast improvement of machine learning, reinforcement learning (RL) has been used
to automate human tasks in different areas. However, training such agents is difficult and …

We present NavACL, a method of automatic curriculum learning tailored to the navigation
task. NavACL is simple to train and efficiently selects relevant tasks using geometric …

The ability to discover useful behaviours from past experience and transfer them to new
tasks is considered a core component of natural embodied intelligence. Inspired by …

In deep reinforcement learning, network convergence speed is often slow and easily
converges to local optimal solutions. For an environment with reward saltation, we propose …

The ability to navigate from visual observations in unfamiliar environments is a core
component of intelligent agents and an ongoing challenge for Deep Reinforcement …

Prevailing offline reinforcement learning (RL) methods limit the policy within the area
supported by the offline dataset to avoid the distributional shift problem. But potential high …