English
Related papers

Related papers: Verification of indefinite-horizon POMDPs

200 papers

Probabilistic hyperproperties describe probabilistic relations between multiple sets of executions in a stochastic system. Prominent examples include information-theoretic characterizations of security and privacy policies. However, model…

Logic in Computer Science · Computer Science 2026-04-09 Lina Gerlach , Tobias Winkler , Erika Ábrahám , Borzoo Bonakdarpour , Sebastian Junges

Empirical investigations into unintended model behavior often show that the algorithm is predicting another outcome than what was intended. These exposes highlight the need to identify when algorithms predict unintended quantities - ideally…

Methodology · Statistics 2026-01-27 Amanda Coston

Design and control of autonomous systems that operate in uncertain or adversarial environments can be facilitated by formal modelling and analysis. Probabilistic model checking is a technique to automatically verify, for a given temporal…

Logic in Computer Science · Computer Science 2021-11-23 Marta Kwiatkowska , Gethin Norman , David Parker

Planning under partial obervability is essential for autonomous robots. A principled way to address such planning problems is the Partially Observable Markov Decision Process (POMDP). Although solving POMDPs is computationally intractable,…

Artificial Intelligence · Computer Science 2020-11-05 Marcus Hoerger , Hanna Kurniawati

Off-policy policy estimators that use importance sampling (IS) can suffer from high variance in long-horizon domains, and there has been particular excitement over new IS methods that leverage the structure of Markov decision processes. We…

Machine Learning · Computer Science 2020-06-09 Yao Liu , Pierre-Luc Bacon , Emma Brunskill

The partial monitoring (PM) framework provides a theoretical formulation of sequential learning problems with incomplete feedback. On each round, a learning agent plays an action while the environment simultaneously chooses an outcome. The…

Machine Learning · Computer Science 2024-05-17 Maxime Heuillet , Ola Ahmad , Audrey Durand

We show that for several variations of partially observable Markov decision processes, polynomial-time algorithms for finding control policies are unlikely to or simply don't have guarantees of finding policies within a constant factor or a…

Artificial Intelligence · Computer Science 2011-06-02 J. Goldsmith , C. Lusena , M. Mundhenk

Partially Observable Markov Decision Processes (POMDPs) are rich environments often used in machine learning. But the issue of information and causal structures in POMDPs has been relatively little studied. This paper presents the concepts…

Artificial Intelligence · Computer Science 2018-01-16 Stuart Armstrong

We present a new proof rule for verifying lower bounds on quantities of probabilistic programs. Our proof rule is not confined to almost-surely terminating programs -- as is the case for existing rules -- and can be used to establish…

Logic in Computer Science · Computer Science 2023-02-14 Shenghua Feng , Mingshuai Chen , Han Su , Benjamin Lucien Kaminski , Joost-Pieter Katoen , Naijun Zhan

Partially observable Markov decision processes (POMDPs) are a fundamental model for sequential decision-making under uncertainty. However, many verification and synthesis problems for POMDPs are undecidable or intractable. Most prominently,…

Artificial Intelligence · Computer Science 2026-04-23 Nathanaël Fijalkow , Arka Ghosh , Roman Kniazev , Guillermo A. Pérez , Pierre Vandenhove

This paper studies discrete-time average-cost infinite-horizon Markov decision processes (MDPs) with Borel state and action sets. It introduces new sufficient conditions for { the} validity of optimality inequalities and optimality…

Optimization and Control · Mathematics 2025-01-28 Eugene A. Feinberg , Pavlo O. Kasyanov , Liliia S. Paliichuk

Hierarchical Reinforcement Learning (HRL) approaches have shown successful results in solving a large variety of complex, structured, long-horizon problems. Nevertheless, a full theoretical understanding of this empirical evidence is…

Machine Learning · Computer Science 2025-02-05 Gianluca Drappo , Alberto Maria Metelli , Marcello Restelli

Automated synthesis of correct-by-construction controllers for autonomous systems is crucial for their deployment in safety-critical scenarios. Such autonomous systems are naturally modeled as stochastic dynamical models. The general…

Systems and Control · Electrical Eng. & Systems 2023-11-17 Thom Badings , Nils Jansen , Licio Romao , Alessandro Abate

We study the detection problem for a finite set of Markov decision processes (MDPs) where the MDPs have the same state and action spaces but possibly different probabilistic transition functions. Any one of these MDPs could be the model for…

Optimization and Control · Mathematics 2021-12-24 Xiaoming Duan , Yagiz Savas , Rui Yan , Zhe Xu , Ufuk Topcu

We address the multiple testing problem under the assumption that the true/false hypotheses are driven by a Hidden Markov Model (HMM), which is recognized as a fundamental setting to model multiple testing under dependence since the seminal…

Methodology · Statistics 2021-05-04 Marie Perrot-Dockès , Gilles Blanchard , Pierre Neuvial , Etienne Roquain

We study strategy synthesis for partially observable Markov decision processes (POMDPs). The particular problem is to determine strategies that provably adhere to (probabilistic) temporal logic constraints. This problem is computationally…

Artificial Intelligence · Computer Science 2019-03-22 Steven Carr , Nils Jansen , Ralf Wimmer , Alexandru C. Serban , Bernd Becker , Ufuk Topcu

Many medical decision-making tasks can be framed as partially observed Markov decision processes (POMDPs). However, prevailing two-stage approaches that first learn a POMDP and then solve it often fail because the model that best fits the…

Machine Learning · Statistics 2020-04-01 Joseph Futoma , Michael C. Hughes , Finale Doshi-Velez

Policy gradient methods are widely used in reinforcement learning. Yet, the nonconvexity of policy optimization poses significant challenges in understanding the global convergence of policy gradient methods. For a class of finite-horizon…

Optimization and Control · Mathematics 2026-03-10 Xin Chen , Yifan Hu , Minda Zhao

Obviously strategyproof (OSP) mechanisms maintain the incentive compatibility of agents that are not fully rational. They have been object of a number of studies since their recent definition. A research agenda, initiated in…

Computer Science and Game Theory · Computer Science 2018-04-30 Diodato Ferraioli , Carmine Ventre

Robots often face challenges in domestic environments where visual feedback is ineffective, such as retrieving objects obstructed by occlusions or finding a light switch in the dark. In these cases, utilizing contacts to localize the target…

Robotics · Computer Science 2024-09-30 Muhammad Suhail Saleem , Rishi Veerapaneni , Maxim Likhachev