English
Related papers

Related papers: Policy evaluation from a single path: Multi-step m…

200 papers

Labeled continuous-time Markov chains (CTMCs) describe processes subject to random timing and partial observability. In applications such as runtime monitoring, we must incorporate past observations. The timing of these observations matters…

Logic in Computer Science · Computer Science 2024-01-30 Thom Badings , Matthias Volk , Sebastian Junges , Marielle Stoelinga , Nils Jansen

Partially Observable Markov Decision Processes (POMDPs) are powerful models for sequential decision making under transition and observation uncertainties. This paper studies the challenging yet important problem in POMDPs known as the…

Artificial Intelligence · Computer Science 2024-06-06 Qi Heng Ho , Martin S. Feather , Federico Rossi , Zachary N. Sunberg , Morteza Lahijanian

Discrete-time Markov Chains (MCs) and Markov Decision Processes (MDPs) are two standard formalisms in system analysis. Their main associated quantitative objectives are hitting probabilities, discounted sum, and mean payoff. Although there…

Data Structures and Algorithms · Computer Science 2020-04-21 Ali Asadi , Krishnendu Chatterjee , Amir Kafshdar Goharshady , Kiarash Mohammadi , Andreas Pavlogiannis

The goal of this paper is to study a distributed version of the gradient temporal-difference (GTD) learning algorithm for multi-agent Markov decision processes (MDPs). The temporal difference (TD) learning is a reinforcement learning (RL)…

Optimization and Control · Mathematics 2018-08-23 Donghwan Lee , Hyungjin Yoon , Naira Hovakimyan

This paper is devoted to solving a time-inconsistent risk-sensitive control problem with parameter $\e$ and its limit case ($\e\rightarrow0^+$) for countable-stated Markov decision processes (MDPs for short). Since the cost functional is…

Optimization and Control · Mathematics 2020-10-22 Hongwei Mei

Reinforcement learning in non-stationary environments is challenging due to abrupt and unpredictable changes in dynamics, often causing traditional algorithms to fail to converge. However, in many real-world cases, non-stationarity has some…

Machine Learning · Computer Science 2025-03-25 Mohsen Amiri , Sindri Magnússon

We consider the problem of constrained Markov Decision Process (CMDP) where an agent interacts with a unichain Markov Decision Process. At every interaction, the agent obtains a reward. Further, there are $K$ cost functions. The agent aims…

Machine Learning · Computer Science 2022-06-22 Mridul Agarwal , Qinbo Bai , Vaneet Aggarwal

We establish a connection between policy evaluation in Markov decision processes and PageRank in network analysis. For a fixed policy, we show that the value function of a discounted Markov decision process can be obtained, up to an…

Optimization and Control · Mathematics 2026-05-04 Konstantin Avrachenkov , Lorenzo Gregoris , Nelly Litvak

Constrained decision-making is essential for designing safe policies in real-world control systems, yet simulated environments often fail to capture real-world adversities. We consider the problem of learning a policy that will maximize the…

Machine Learning · Computer Science 2026-02-10 Sourav Ganguly , Kishan Panaganti , Arnob Ghosh , Adam Wierman

In this work, we consider the popular tree-based search strategy within the framework of reinforcement learning, the Monte Carlo Tree Search (MCTS), in the context of infinite-horizon discounted cost Markov Decision Process (MDP). While…

Machine Learning · Statistics 2020-01-14 Devavrat Shah , Qiaomin Xie , Zhi Xu

We consider Markov decision processes (MDPs) in which the transition probabilities and rewards belong to an uncertainty set parametrized by a collection of random variables. The probability distributions for these random parameters are…

Logic in Computer Science · Computer Science 2020-02-26 Murat Cubuktepe , Nils Jansen , Sebastian Junges , Joost-Pieter Katoen , Ufuk Topcu

In Markov Decision Processes (MDPs), the reward obtained in a state depends on the properties of the last state and action. This state dependency makes it difficult to reward more interesting long-term behaviors, such as always closing a…

Artificial Intelligence · Computer Science 2017-06-27 Ronen Brafman , Giuseppe De Giacomo , Fabio Patrizi

This article introduces a sensitivity analysis method for Multiple Testing Procedures (MTPs) using marginal $p$-values. The method is based on the Dirichlet process (DP) prior distribution, specified to support the entire space of MTPs,…

Methodology · Statistics 2025-09-19 George Karabatsos

In reinforcement learning, temporal difference (TD) is the most direct algorithm to learn the value function of a policy. For large or infinite state spaces, exact representations of the value function are usually not available, and it must…

Machine Learning · Computer Science 2018-05-03 Yann Ollivier

We study the evaluation of a policy under best- and worst-case perturbations to a Markov decision process (MDP), using transition observations from the original MDP, whether they are generated under the same or a different policy. This is…

Artificial Intelligence · Computer Science 2024-11-05 Andrew Bennett , Nathan Kallus , Miruna Oprescu , Wen Sun , Kaiwen Wang

This paper considers an infinite-horizon Markov decision process (MDP) that allows for general non-exponential discount functions, in both discrete and continuous time. Due to the inherent time inconsistency, we look for a randomized…

Optimization and Control · Mathematics 2024-12-10 Erhan Bayraktar , Yu-Jui Huang , Zhenhua Wang , Zhou Zhou

The linear Markov Decision Process (MDP) framework offers a principled foundation for reinforcement learning (RL) with strong theoretical guarantees and sample efficiency. However, its restrictive assumption-that both transition dynamics…

Machine Learning · Statistics 2025-06-03 Sinian Zhang , Kaicheng Zhang , Ziping Xu , Tianxi Cai , Doudou Zhou

In an Markov decision process (MDP), unobservable confounders may exist and have impacts on the data generating process, so that the classic off-policy evaluation (OPE) estimators may fail to identify the true value function of the target…

Machine Learning · Statistics 2022-09-13 Miao Lu , Wenhao Yang , Liangyu Zhang , Zhihua Zhang

We tackle the problem of acting in an unknown finite and discrete Markov Decision Process (MDP) for which the expected shortest path from any state to any other state is bounded by a finite number $D$. An MDP consists of $S$ states and $A$…

Machine Learning · Computer Science 2019-07-11 Aristide Tossou , Christos Dimitrakakis , Debabrota Basu

We study the problem of learning optimal policies in finite-horizon Markov Decision Processes (MDPs) using low-rank reinforcement learning (RL) methods. In finite-horizon MDPs, the policies, and therefore the value functions (VFs) are not…

Machine Learning · Computer Science 2026-05-14 Sergio Rozada , Jose Luis Orejuela , Antonio G. Marques