From the 1 of 16 linked papers with an AI index.
16 papers
Property-driven Causal Abstractions for Markov Decision Processes
Jule Schmidt, Maximilian Weininger, Clemens Dubslaff +2
The paper proposes a property-driven causal abstraction method for factored Markov Decision Processes that groups states sharing the same causal reasons for satisfying or violating…
dtControl2+: Trading Optimality for Explainability in MDPs via Decision Trees
Tereza Kinská, Jan KÅetÃnský, Tobias Meggendorfer +2
Over the past decade, decision trees have been used to represent controllers (a.k.a. policies) in an explainable way, with dtControl2 as a current state-of-the-art tool. However, f…
Confidence Sequences for Online Statistical Model Checking of Markov Decision Processes
Konstantin Kueffner, Tobias Meggendorfer, Maximilian Weininger +1
Markov decision processes (MDPs) are a classic model of decision making under uncertainty, exhibiting both non-deterministic choice as well as probabilistic uncertainty. Traditiona…
UMB: A Unified Markov Binary Format for Probabilistic Model Checking (extended version)
Roman Andriushchenko, Arnd Hartmanns, Joshua Jeppson +5
This paper presents the unified Markov binary (UMB) format, an efficient, extensible, and well-supported explicit-state file format for representing a wide range of probabilistic s…
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…
Sound Value Iteration for Simple Stochastic Games
Muqsit Azeem, Jan Kretinsky, Maximilian Weininger
Algorithmic analysis of Markov decision processes (MDP) and stochastic games (SG) in practice relies on value-iteration (VI) algorithms. Since the basic version of VI does not prov…