7 papers
Can You Trust Your Preference Models? Stackelberg Games for Alignment
Riccardo Formenti, Aditya Agrawal, Vikas Garg
Language models are frequently aligned to human preferences via imperfect evaluators whose errors can be exploited during optimization. We train policies to search for comparisons…
Multi-Environment POMDPs: Discrete Model Uncertainty Under Partial Observability
Eline M. Bovy, Caleb Probine, Marnix Suilen +2
Multi-environment POMDPs (ME-POMDPs) extend standard POMDPs with discrete model uncertainty. ME-POMDPs represent a finite set of POMDPs that share the same state, action, and obser…
Robust Finite-Memory Policy Gradients for Hidden-Model POMDPs
Maris F. L. Galesloot, Roman Andriushchenko, Milan Češka +2
Partially observable Markov decision processes (POMDPs) model specific environments in sequential decision-making under uncertainty. Critically, optimal policies for POMDPs may not…
Approximate Dec-POMDP Solving Using Multi-Agent A*
Wietze Koops, Sebastian Junges, Nils Jansen
We present an A*-based algorithm to compute policies for finite-horizon Dec-POMDPs. Our goal is to sacrifice optimality in favor of scalability for larger horizons. The main ingred…
Imprecise Probabilities Meet Partial Observability: Game Semantics for Robust POMDPs
Eline M. Bovy, Marnix Suilen, Sebastian Junges +1
Partially observable Markov decision processes (POMDPs) rely on the key assumption that probability distributions are precisely known. Robust POMDPs (RPOMDPs) alleviate this concer…
Robust Policy Synthesis for Uncertain POMDPs via Convex Optimization
Marnix Suilen, Nils Jansen, Murat Cubuktepe +1
We study the problem of policy synthesis for uncertain partially observable Markov decision processes (uPOMDPs). The transition probability function of uPOMDPs is only known to bel…
Strategy Synthesis in POMDPs via Game-Based Abstractions
Leonore Winterer, Sebastian Junges, Ralf Wimmer +4
We study synthesis problems with constraints in partially observable Markov decision processes (POMDPs), where the objective is to compute a strategy for an agent that is guarantee…