Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleSeptember 2024
Probabilistic reach-avoid for Bayesian neural networks
AbstractModel-based reinforcement learning seeks to simultaneously learn the dynamics of an unknown stochastic environment and synthesise an optimal policy for acting in it. Ensuring the safety and robustness of sequential decisions made through a policy ...
- ArticleJuly 2024
Bisimulation Learning
AbstractWe introduce a data-driven approach to computing finite bisimulations for state transition systems with very large, possibly infinite state space. Our novel technique computes stutter-insensitive bisimulations of deterministic systems, which we ...
- articleJuly 2024
Symbolic Task Inference in Deep Reinforcement Learning
This paper proposes DeepSynth, a method for effective training of deep reinforcement learning agents when the reward is sparse or non-Markovian, but at the same time progress towards the reward requires achieving an unknown sequence of high-level ...
Fossil 2.0: Formal Certificate Synthesis for the Verification and Control of Dynamical Models
HSCC '24: Proceedings of the 27th ACM International Conference on Hybrid Systems: Computation and ControlArticle No.: 26, Pages 1–10https://doi.org/10.1145/3641513.3651398This paper presents Fossil 2.0, a new major release of a software tool for the synthesis of certificates (e.g., Lyapunov and barrier functions) for dynamical systems modelled as ordinary differential and difference equations. Fossil 2.0 is much improved ...
-
- research-articleMay 2024
CTL Model Checking of MDPs over Distribution Spaces: Algorithms and Sampling-based Computations
HSCC '24: Proceedings of the 27th ACM International Conference on Hybrid Systems: Computation and ControlArticle No.: 20, Pages 1–12https://doi.org/10.1145/3641513.3651397This work studies computation tree logic (CTL) model checking for finite-state Markov decision processes (MDPs) over the space of their distributions. Instead of investigating properties over states of the MDP, as encoded by formulae in standard ...
- introductionNovember 2023
- ArticleSeptember 2023
Formal Controller Synthesis for Markov Jump Linear Systems with Uncertain Dynamics
AbstractAutomated synthesis of provably correct controllers for cyber-physical systems is crucial for deployment in safety-critical scenarios. However, hybrid features and stochastic or unknown behaviours make this problem challenging. We propose a method ...
- ArticleSeptember 2023
- research-articleSeptember 2023
Certified reinforcement learning with logic guidance
AbstractReinforcement Learning (RL) is a widely employed machine learning architecture that has been applied to a variety of control problems. However, applications in safety-critical domains require a systematic and formal approach to ...
- research-articleJuly 2023
On the limitations of Markovian rewards to express multi-objective, risk-sensitive, and modal tasks
UAI '23: Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial IntelligenceArticle No.: 185, Pages 1974–1984In this paper, we study the expressivity of scalar, Markovian reward functions in Reinforcement Learning (RL), and identify several limitations to what they can express. Specifically, we look at three classes of RL tasks; multi-objective RL, risk-...
- research-articleJuly 2023
Invariance in policy optimisation and partial identifiability in reward learning
ICML'23: Proceedings of the 40th International Conference on Machine LearningArticle No.: 1328, Pages 32033–32058It is often very challenging to manually design reward functions for complex, real-world tasks. To solve this, one can instead use reward learning to infer a reward function from data. However, there are often multiple reward functions that fit the data ...
- research-articleJuly 2023
Reasoning about causality in games
AbstractCausal reasoning and game-theoretic reasoning are fundamental topics in artificial intelligence, among many other disciplines: this paper is concerned with their intersection. Despite their importance, a formal framework that supports ...
- research-articleMay 2023
k-Prize Weighted Voting Game
- Wei-Chen Lee,
- David Hyland,
- Alessandro Abate,
- Edith Elkind,
- Jiarui Gan,
- Julian Gutierrez,
- Paul Harrenstein,
- Michael Wooldridge
AAMAS '23: Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent SystemsPages 2049–2057We introduce a natural variant of weighted voting games, which we refer to as k-Prize Weighted Voting Games. Such games consist of n players with weights, and k prizes, of possibly differing values. The players form coalitions, and the i-th largest ...
- research-articleMay 2023
- articleMay 2023
Robust Control for Dynamical Systems with Non-Gaussian Noise via Formal Abstractions
- Thom Badings,
- Licio Romao,
- Alessandro Abate,
- David Parker,
- Hasan A. Poonawala,
- Marielle Stoelinga,
- Nils Jansen
Controllers for dynamical systems that operate in safety-critical settings must account for stochastic disturbances. Such disturbances are often modeled as process noise in a dynamical system, and common assumptions are that the underlying distributions ...
- research-articleFebruary 2023
Misspecification in inverse reinforcement learning
AAAI'23/IAAI'23/EAAI'23: Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence and Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence and Thirteenth Symposium on Educational Advances in Artificial IntelligenceArticle No.: 1697, Pages 15136–15143https://doi.org/10.1609/aaai.v37i12.26766The aim of Inverse Reinforcement Learning (IRL) is to infer a reward function R from a policy π. To do this, we need a model of how π relates to R. In the current literature, the most common models are optimality, Boltzmann rationality, and causal entropy ...
- research-articleFebruary 2023
Probabilities are not enough: formal controller synthesis for stochastic dynamical models with epistemic uncertainty
AAAI'23/IAAI'23/EAAI'23: Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence and Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence and Thirteenth Symposium on Educational Advances in Artificial IntelligenceArticle No.: 1649, Pages 14701–14710https://doi.org/10.1609/aaai.v37i12.26718Capturing uncertainty in models of complex dynamical systems is crucial to designing safe controllers. Stochastic noise causes aleatoric uncertainty, whereas imprecise knowledge of model parameters leads to epistemic uncertainty. Several approaches use ...
- research-articleFebruary 2023
Low emission building control with zero-shot reinforcement learning
AAAI'23/IAAI'23/EAAI'23: Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence and Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence and Thirteenth Symposium on Educational Advances in Artificial IntelligenceArticle No.: 1599, Pages 14259–14267https://doi.org/10.1609/aaai.v37i12.26668Heating and cooling systems in buildings account for 31% of global energy use, much of which are regulated by Rule Based Controllers (RBCs) that neither maximise energy efficiency nor minimise emissions by interacting optimally with the grid. Control via ...
- research-articleDecember 2022
Automated verification and synthesis of stochastic hybrid systems: A survey
Automatica (Journal of IFAC) (AJIF), Volume 146, Issue Chttps://doi.org/10.1016/j.automatica.2022.110617AbstractStochastic hybrid systems have received significant attentions as a relevant modeling framework describing many systems, from engineering to the life sciences: they enable the study of numerous applications, including transportation ...