In recent years, reinforcement learning (RL) systems have shown impressive performance
and remarkable achievements. Many achievements can be attributed to combining RL with …

Traditional reinforcement learning methods are only applicable to single-scenario tasks.
When it comes to multi-scenario, the single-scenario agents fail to perform well. That is, the …

In this chapter, we review existing work from the emerging research on global explanations
of reinforcement learning (RL) agents. This is an important area of research in explainable …

Decision Trees (DTs) constitute one of the major highly non-linear AI models, valued, eg, for
their efficiency on tabular data. Learning accurate DTs is, however, complicated, especially …

Reinforcement learning (RL) has seen significant success across various domains, but its
adoption is often limited by the black-box nature of neural network policies, making them …

We consider the problem of verifying complex learned controllers using distillation. In
contrast to previous work, we require that the distilled model maintains behavioural fidelity …

Explainable reinforcement learning has evolved rapidly over the years because
transparency of the model's decision-making process is crucial in some important domains …

As progress in AI impacts all sectors of society, the world is destined to see increasingly
complex and numerous autonomous decision-making agents, which act upon their …