5 papers
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…
Robust Probabilistic Shielding for Safe Offline Reinforcement Learning
Maris F. L. Galesloot, Thomas Rhemrev, Nils Jansen
In offline reinforcement learning (RL), we learn policies from fixed datasets without environment interaction. The major challenges are to provide guarantees on the (1) performance…
Perception-Based Beliefs for POMDPs with Visual Observations
Miriam Schäfers, Merlijn Krale, Thiago D. Simão +2
Partially observable Markov decision processes (POMDPs) are a principled planning model for sequential decision-making under uncertainty. Yet, real-world problems with high-dimensi…
Pessimistic Iterative Planning with RNNs for Robust POMDPs
Maris F. L. Galesloot, Marnix Suilen, Thiago D. Simão +4
Robust POMDPs extend classical POMDPs to incorporate model uncertainty using so-called uncertainty sets on the transition and observation functions, effectively defining ranges of…
Tighter Value-Function Approximations for POMDPs
Merlijn Krale, Wietze Koops, Sebastian Junges +2
Solving partially observable Markov decision processes (POMDPs) typically requires reasoning about the values of exponentially many state beliefs. Towards practical performance, st…