Safety is critical to broadening the application of reinforcement learni...
In an offline reinforcement learning setting, the safe policy improvemen...
We provide a novel method for sensitivity analysis of parametric robust
...
We study Markov decision processes (MDPs), where agents have direct cont...
This position paper reflects on the state-of-the-art in decision-making ...
Multiple-environment MDPs (MEMDPs) capture finite sets of MDPs that shar...
We study safe policy improvement (SPI) for partially observable Markov
d...
Controllers for dynamical systems that operate in safety-critical settin...
Deep Reinforcement Learning (RL) agents are susceptible to adversarial n...
Automated synthesis of provably correct controllers for cyber-physical
s...
Capturing uncertainty in models of complex dynamical systems is crucial ...
We address the problem of safe reinforcement learning from pixel
observa...
This paper presents COOL-MC, a tool that integrates state-of-the-art
rei...
Cost-effective asset management is an area of interest across several
in...
This paper surveys the analysis of parametric Markov models whose transi...
Markov decision processes (MDPs) are formal models commonly used in
sequ...
We employ uncertain parametric CTMCs with parametric transition rates an...
Reinforcement learning (RL) in safety-critical environments requires an ...
We consider parametric Markov decision processes (pMDPs) that are augmen...
Controllers for autonomous systems that operate in safety-critical setti...
Probabilistic model checking aims to prove whether a Markov decision pro...
This paper outlines two approaches|based on counterexample-guided abstra...
We study planning problems for continuous control systems with uncertain...
We investigate the capabilities of transfer learning in the area of
stru...
This paper targets control problems that exhibit specific safety and
per...
Uncertain partially observable Markov decision processes (uPOMDPs) allow...
Detection of military assets on the ground can be performed by applying ...
The synthesis problem for partially observable Markov decision processes...
Partially-Observable Markov Decision Processes (POMDPs) are a well-known...
Robot capabilities are maturing across domains, from self-driving cars, ...
We give a formal verification procedure that decides whether a classifie...
Recurrent neural networks (RNNs) have emerged as an effective representa...
We consider Markov decision processes (MDPs) in which the transition
pro...
We present the Neural Simplex Architecture (NSA), a new approach to runt...
We synthesize shared control protocols subject to probabilistic temporal...
We study strategy synthesis for partially observable Markov decision
pro...
Markov chain analysis is a key technique in reliability engineering. A
p...
This paper considers large families of Markov chains (MCs) that are defi...
Progressively intricate cyber infiltration mechanisms have made conventi...
We introduce the concept of structured synthesis for Markov decision
pro...
A prominent problem in artificial intelligence and machine learning is t...
We study planning problems where autonomous agents operate inside
enviro...
We study finite-state controllers (FSCs) for partially observable Markov...
We study motion planning problems where agents move inside environments ...
This paper proposes to use probabilistic model checking to synthesize op...
We formalize synthesis of shared control protocols with correctness
guar...