An emerging branch of control theory specialises in certificate learning...
Neural abstractions have been recently introduced as formal approximatio...
Multi-agent influence diagrams (MAIDs) are a popular game-theoretic mode...
We introduce networked communication to the mean-field game framework. I...
We introduce an adaptive refinement procedure for smart, and scalable
ab...
Distributional reinforcement learning (DRL) enhances the understanding o...
We introduce a natural variant of weighted voting games, which we refer ...
We present a novel method for the safety verification of nonlinear dynam...
We present a machine learning approach to quantitative verification. We
...
Causal reasoning and game-theoretic reasoning are fundamental topics in
...
Controllers for dynamical systems that operate in safety-critical settin...
In this work we introduce reinforcement learning techniques for solving
...
The aim of Inverse Reinforcement Learning (IRL) is to infer a reward fun...
Automated synthesis of provably correct controllers for cyber-physical
s...
Capturing uncertainty in models of complex dynamical systems is crucial ...
Policy robustness in Reinforcement Learning (RL) may not be desirable at...
LCRL is a software tool that implements model-free Reinforcement Learnin...
Training reinforcement learning (RL) agents using scalar reward signals ...
Heating and cooling systems in buildings account for 31% of global energ...
It's challenging to design reward functions for complex, real-world task...
Controllers for autonomous systems that operate in safety-critical setti...
We consider the problem of computing reach-avoid probabilities for itera...
We work with continuous-time, continuous-space stochastic dynamical syst...
This paper investigates the motion planning of autonomous dynamical syst...
Multi-agent influence diagrams (MAIDs) are a popular form of graphical m...
In this paper, we study the problem of learning to satisfy temporal logi...
Stochastic hybrid systems have received significant attentions as a rele...
SafePILCO is a software tool for safe and data-efficient policy search w...
In this paper we employ SMT solvers to soundly synthesise Lyapunov funct...
This work discusses the reachability analysis (RA) of Max-Plus Linear (M...
We introduce an automated, formal, counterexample-based approach to
synt...
In Hierarchical Control, compositionality, abstraction, and task-transfe...
This paper proposes a new approach, grounded in Satisfiability Modulo
Th...
We propose a new technique to accelerate algorithms based on Gradient De...
Given a discrete probability measure supported on N atoms and a set of n...
We present a data-driven verification approach that determines whether o...
We propose an automated and sound technique to synthesize provably corre...
This paper presents the concept of an adaptive safe padding that forces
...
Gaussian Processes (GPs) are widely employed in control and learning bec...
We propose a method for effective training of deep Reinforcement Learnin...
We propose a method for efficient training of deep Reinforcement Learnin...
We propose an actor-critic, model-free, and online Reinforcement Learnin...
There is a scalability gap between probabilistic and non-probabilistic
v...
Reinforcement Learning (RL) has emerged as an efficient method of choice...
This paper introduces the abstraction of max-plus linear (MPL) systems v...
This paper proposes the first model-free Reinforcement Learning (RL)
fra...
This paper proposes a method for efficient training of the Q-function fo...
We propose a novel Reinforcement Learning (RL) algorithm to synthesize
p...
Cyber-physical systems, like Smart Buildings and power plants, have to m...
The formal verification and controller synthesis for Markov decision
pro...