Data-efficient learning algorithms are essential in many practical applications where data
collection is expensive, eg, in robotics due to the wear and tear. To address this problem …

A long-term goal of reinforcement learning agents is to be able to perform tasks in complex
real-world scenarios. The use of external information is one way of scaling agents to more …

Interactive reinforcement learning proposes the use of externally sourced information in
order to speed up the learning process. When interacting with a learner agent, humans may …

Experience replay plays a crucial role in improving the sample efficiency of deep
reinforcement learning agents. Recent advances in experience replay propose using Mixup …

Federated Reinforcement Learning (FRL) has garnered increasing attention recently.
However, due to the intrinsic spatio-temporal non-stationarity of data distributions, the …

Enhancing traffic signal optimisation has the potential to improve urban traffic flow without
the need for expensive infrastructure modifications. While reinforcement learning (RL) …

Automated systems, controlled with programmed reactive rules and set-point values for
feedback regulation, require supervision and adjustment by experienced technicians. These …

Riverbed Modeler is a useful simulation tool that can simulate a variety of standard network
models. However, it does not provide a related tool that does not suit the situation in which …

We proposed the Sparse Bayesian Network-based Disturbance Observer (SBN-DOB) to
enhance the robustness of policy-based reinforcement learning. SBN-DOB utilizes sparse …

Production and scheduling planning are central functions in manufacturing industries whose
relevance is increasingly important due to the complexity of the operations required to …