Abstract Offline Learning from Demonstrations (OLfD) is valuable in domains where trial-and-
error learning is infeasible or specifying a cost function is difficult, such as robotic surgery …

Many networking tasks now employ deep learning (DL) to solve complex prediction and
system optimization problems. However, current design philosophy of DL-based algorithms …

Human beings can make adaptive decisions in a preparatory manner, ie, by making
preparations in advance, which offers significant advantages in scenarios where both online …

Offline model selection (OMS), that is, choosing the best policy from a set of many policies
given only logged data, is crucial for applying offline RL in real-world settings. One idea that …

In recent years, various machine learning (ML) solutions have been developed to solve
resource management, interference management, autonomy, and decision-making …

In offline actor–critic (AC) algorithms, the distributional shift between the training data and
target policy causes optimistic value estimates for out-of-distribution (OOD) actions. This …

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 introduce a proof of concept to parametrise the unresolved subgrid scale of sea-ice
dynamics with deep learning techniques. Instead of parametrising single processes, a single …

Active perception describes a broad class of techniques that couple planning and
perception systems to move the robot in a way to give the robot more information about the …

Multi-agent Reinforcement Learning (MARL) has gained wide attention in recent years and
has made progress in various fields. Specifically, cooperative MARL focuses on training a …