Milan Ceska — accepted AI-conference papers

2025

Robust Finite-Memory Policy Gradients for Hidden-Model POMDPs

Maris F. L. Galesloot, Roman Andriushchenko, Milan Ceska, Sebastian Junges, Nils Jansen

IJCAI 2025

Partially observable Markov decision processes (POMDPs) model specific environments in sequential decision-making under uncertainty. Critically, optimal policies for POMDPs may not be robust against perturbations in the environment. Hidden-model POMDPs (HM-POMDPs) capture sets of different environme

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Symbiotic Local Search for Small Decision Tree Policies in MDPs

Roman Andriushchenko, Milan Ceska, Debraj Chakraborty, Sebastian Junges, Jan Kretinsky, Filip Macák

UAI 2025

We study decision making policies in Markov decision processes (MDPs). Two key performance indicators of such policies are their value and their interpretability. On the one hand, policies that optimize value can be efficiently computed via a plethora of standard methods. However, the representation

Cited by 0 Source ↗PDF ↗Scholar ↗