Although deep reinforcement learning has become a promising machine learning approach
for sequential decision-making problems, it is still not mature enough for high-stake domains …

Deep reinforcement learning (DRL) has gained great success by learning directly from high-
dimensional sensory inputs, yet is notorious for the lack of interpretability. Interpretability of …

Reinforcement Learning (RL), bolstered by the expressive capabilities of Deep Neural
Networks (DNNs) for function approximation, has demonstrated considerable success in …

Deploying deep reinforcement learning in safety-critical settings requires developing
algorithms that obey hard constraints during exploration. This paper contributes a first …

Robots frequently face complex tasks that require more than one action, where sequential
decision-making (sdm) capabilities become necessary. The key contribution of this work is a …

Reinforcement Learning (RL), bolstered by the expressive capabilities of Deep Neural
Networks (DNNs) for function approximation, has demonstrated considerable success in …

Recently deep reinforcement learning has achieved tremendous success in wide ranges of
applications. However, it notoriously lacks data-efficiency and interpretability. Data-efficiency …

To be responsive to dynamically changing real-world environments, an intelligent agent
needs to perform complex sequential decision-making tasks that are often guided by …

Abstract Knowledge Reasoning (KR) has become the core issue in the field of Artificial
Intelligence (AI) and even Natural Language Processing (NLP). KR based on Knowledge …

One important aspect of autonomous driving lies in the selection of maneuver sequences.
Here the challenge is to optimize the driving comfort and travel-duration, while always …