1 citations · 2 across the 4 of their papers we have counts for
8 papers
Fast Computation of Conditional Probabilities in MDPs and Markov Chain Families
Milan ÄeÅ¡ka, Sebastian Junges, Luko van der Maas +2
Computing optimal conditional reachability probabilities in Markov decision processes (MDPs) is tractable by a reduction to reachability probabilities. Yet, this reduction yields c…
Shields to Guarantee Probabilistic Safety in MDPs
Linus Heck, Filip Macák, Roman Andriushchenko +2
Shielding is a prominent model-based technique to ensure safety of autonomous agents. Classical shielding aims to ensure that nothing bad ever happens and comes with strong guarant…
Missingness-MDPs: Bridging the Theory of Missing Data and POMDPs
Joshua Wendland, Markel Zubia, Roman Andriushchenko +6
We introduce missingness-MDPs (miss-MDPs), a novel subclass of partially observable Markov decision processes (POMDPs) that incorporates the theory of missing data. A miss-MDP is a…
Finite-State Controllers for (Hidden-Model) POMDPs using Deep Reinforcement Learning
David Hudák, Maris F. L. Galesloot, Martin Tappler +3
Solving partially observable Markov decision processes (POMDPs) requires computing policies under imperfect state information. Despite recent advances, the scalability of existing…
Constrained and Robust Policy Synthesis with Satisfiability-Modulo-Probabilistic-Model-Checking
Linus Heck, Filip Macák, Milan ÄeÅ¡ka +1
The ability to compute reward-optimal policies for given and known finite Markov decision processes (MDPs) underpins a variety of applications across planning, controller synthesis…
Robust Finite-Memory Policy Gradients for Hidden-Model POMDPs
Maris F. L. Galesloot, Roman Andriushchenko, Milan ÄeÅ¡ka +2
Partially observable Markov decision processes (POMDPs) model specific environments in sequential decision-making under uncertainty. Critically, optimal policies for POMDPs may not…