English
Related papers

Related papers: Sound Value Iteration

200 papers

Gaussian Processes (GPs) are widely employed in control and learning because of their principled treatment of uncertainty. However, tracking uncertainty for iterative, multi-step predictions in general leads to an analytically intractable…

This paper considers a risk-constrained motion planning problem and aims to find the solution combining the concepts of iterative model predictive control (MPC) and data-driven distributionally robust (DR) risk-constrained optimization. In…

Optimization and Control · Mathematics 2023-10-09 Alireza Zolanvari , Ashish Cherukuri

We study reinforcement learning in infinite-horizon average-reward settings with linear MDPs. Previous work addresses this problem by approximating the average-reward setting by discounted setting and employing a value iteration-based…

Machine Learning · Computer Science 2025-04-17 Kihyuk Hong , Ambuj Tewari

Robust Markov decision processes (MDPs) allow to compute reliable solutions for dynamic decision problems whose evolution is modeled by rewards and partially-known transition probabilities. Unfortunately, accounting for uncertainty in the…

Machine Learning · Computer Science 2020-06-18 Chin Pang Ho , Marek Petrik , Wolfram Wiesemann

We build on a recently introduced geometric interpretation of Markov Decision Processes (MDPs) to analyze classical MDP-solving algorithms: Value Iteration (VI) and Policy Iteration (PI). First, we develop a geometry-based analytical…

Machine Learning · Computer Science 2025-03-07 Arsenii Mustafin , Aleksei Pakharev , Alex Olshevsky , Ioannis Ch. Paschalidis

Learning-based approaches to verifying unknown Markov decision processes (MDPs) often employ uncertain MDPs. These models use, for example, confidence intervals to capture transition uncertainty and allow synthesis of policies that are…

Machine Learning · Computer Science 2026-05-05 Yannik Schnitzer , Alessandro Abate , David Parker

In multiple criteria decision aiding, very often the alternatives are compared by means of a value function compatible with the preferences expressed by the Decision Maker. The problem is that, in general, there is a plurality of compatible…

Optimization and Control · Mathematics 2023-04-14 Sally Giuseppe Arcidiacono , Salvatore Corrente , Salvatore Greco

In this paper, we present a novel iterative Monte Carlo method for approximating the stationary probability of a single state of a positive recurrent Markov chain. We utilize the characterization that the stationary probability of a state…

Data Structures and Algorithms · Computer Science 2015-12-11 Christina E. Lee , Asuman Ozdaglar , Devavrat Shah

Modified policy iteration (MPI) is a dynamic programming algorithm that combines elements of policy iteration and value iteration. The convergence of MPI has been well studied in the context of discounted and average-cost MDPs. In this…

Machine Learning · Computer Science 2024-02-16 Yashaswini Murthy , Mehrdad Moharrami , R. Srikant

In the Monte Carlo (MC) method statistical noise is usually present. Statistical noise may become dominant in the calculation of a distribution, usually by iteration, but is less Important in calculating integrals. The subject of the…

Computational Physics · Physics 2013-11-08 Mihály Makai , Zoltán Szatmáry

We propose an iterative estimating equations procedure for analysis of longitudinal data. We show that, under very mild conditions, the probability that the procedure converges at an exponential rate tends to one as the sample size…

Statistics Theory · Mathematics 2007-12-18 Jiming Jiang , Yihui Luan , You-Gan Wang

In this paper we provide faster algorithms for approximately solving discounted Markov Decision Processes in multiple parameter regimes. Given a discounted Markov Decision Process (DMDP) with $|S|$ states, $|A|$ actions, discount factor…

Data Structures and Algorithms · Computer Science 2020-12-24 Aaron Sidford , Mengdi Wang , Xian Wu , Yinyu Ye

Parametric Markov chains occur quite naturally in various applications: they can be used for a conservative analysis of probabilistic systems (no matter how the parameter is chosen, the system works to specification); they can be used to…

Logic in Computer Science · Computer Science 2018-11-05 Paul Gainer , Ernst Moritz Hahn , Sven Schewe

Reachability analysis, in general, is a fundamental method that supports formally-correct synthesis, robust model predictive control, set-based observers, fault detection, invariant computation, and conformance checking, to name but a few.…

Systems and Control · Electrical Eng. & Systems 2020-11-17 Niklas Kochdumper , Bastian Schürmann , Matthias Althoff

Reachability analysis evaluates system safety, by identifying the set of states a system may evolve within over a finite time horizon. In contrast to model-based reachability analysis, data-driven reachability analysis estimates reachable…

Systems and Control · Electrical Eng. & Systems 2026-04-06 Elizabeth Dietrich , Hanna Krasowski , Murat Arcak

As modern neural networks get more complex, specifying a model with high predictive performance and sound uncertainty quantification becomes a more challenging task. Despite some promising theoretical results on the true posterior…

Machine Learning · Computer Science 2025-06-18 Alisa Sheinkman , Sara Wade

We study the general approach to accelerating the convergence of the most widely used solution method of Markov decision processes with the total expected discounted reward. Inspired by the monotone behavior of the contraction mappings in…

Optimization and Control · Mathematics 2008-03-28 Oleksandr Shlakhter , Chi-Guhn Lee , Dmitry Khmelev , Nasser Jaber

We propose a simple technique for verifying probabilistic models whose transition probabilities are parametric. The key is to replace parametric transitions by nondeterministic choices of extremal values. Analysing the resulting…

Logic in Computer Science · Computer Science 2016-05-27 Tim Quatmann , Christian Dehnert , Nils Jansen , Sebastian Junges , Joost-Pieter Katoen

In applications of imprecise probability, analysts must compute lower (or upper) expectations, defined as the infimum of an expectation over a set of parameter values. Monte Carlo methods consistently approximate expectations at fixed…

Computation · Statistics 2021-03-05 Nicholas Syring , Ryan Martin

Decision making or scientific discovery pipelines such as job hiring and drug discovery often involve multiple stages: before any resource-intensive step, there is often an initial screening that uses predictions from a machine learning…

Methodology · Statistics 2023-05-30 Ying Jin , Emmanuel J. Candès