This position paper reflects on the state-of-the-art in decision-making under uncertainty. A
classical assumption is that probabilities can sufficiently capture all uncertainty in a system …

Reinforcement learning (RL) can be used to design smart driving policies in complex
situations where traditional methods cannot. However, they are frequently black-box in …

Abstract We present the Neural Simplex Architecture (NSA), a new approach to runtime
assurance that provides safety guarantees for neural controllers (obtained eg using …

We study safe policy improvement (SPI) for partially observable Markov decision processes
(POMDPs). SPI is an offline reinforcement learning (RL) problem that assumes access to (1) …

Deploying reinforcement learning (RL) involves major concerns around safety. Engineering
a reward signal that allows the agent to maximize its performance while remaining safe is …

Algorithms for safely improving policies are important to deploy reinforcement learning
approaches in real-world scenarios. In this work, we propose an algorithm, called MCTS …

Autonomous mobile robots employed in industrial applications often operate in complex and
uncertain environments. In this paper we propose an approach based on an extension of …

The primary challenge in the development of large-scale artificial intelligence (AI) systems
lies in achieving scalable decision-making—extending the AI models while maintaining …

Abstract Batch Reinforcement Learning (Batch RL) consists in training a policy using
trajectories collected with another policy, called the behavioural policy. Safe policy …

Deep reinforcement learning (DRL) has emerged as a promising approach for developing
more intelligent autonomous vehicles (AVs). A typical DRL application on AVs is to train a …