中文
相关论文

相关论文: Efficient Analysis of Polynomial Asymptotic Estima…

200 篇论文

We present a method for solving implicit (factored) Markov decision processes (MDPs) with very large state spaces. We introduce a property of state space partitions which we call epsilon-homogeneity. Intuitively, an epsilon-homogeneous…

人工智能 · 计算机科学 2013-02-08 Thomas L. Dean , Robert Givan , Sonia Leach

We give polynomial-time algorithms for computing the values of Markov decision processes (MDPs) with limsup and liminf objectives. A real-valued reward is assigned to each state, and the value of an infinite path in the MDP is the limsup…

计算机科学与博弈论 · 计算机科学 2008-09-10 Krishnendu Chatterjee , Thomas A. Henzinger

The curse of dimensionality is a widely known issue in reinforcement learning (RL). In the tabular setting where the state space $\mathcal{S}$ and the action space $\mathcal{A}$ are both finite, to obtain a nearly optimal policy with…

机器学习 · 计算机科学 2022-10-28 Bingyan Wang , Yuling Yan , Jianqing Fan

Models of many real-life applications, such as queuing models of communication networks or computing systems, have a countably infinite state-space. Algorithmic and learning procedures that have been developed to produce optimal policies…

系统与控制 · 电气工程与系统科学 2024-03-19 Saghar Adler , Vijay Subramanian

Partially observable Markov decision processes (POMDPs) are a general mathematical model for sequential decision-making in stochastic environments under state uncertainty. POMDPs are often solved \textit{online}, which enables the algorithm…

人工智能 · 计算机科学 2025-03-26 Yunuo Zhang , Baiting Luo , Ayan Mukhopadhyay , Abhishek Dubey

This paper studies Markov Decision Processes (MDPs) with atomless initial state distributions and atomless transition probabilities. Such MDPs are called atomless. The initial state distribution is considered to be fixed. We show that for…

最优化与控制 · 数学 2018-10-26 Eugene A. Feinberg , Aleksey B. Piunovskiy

We study the synthesis of mode switching protocols for a class of discrete-time switched linear systems in which the mode jumps are governed by Markov decision processes (MDPs). We call such systems MDP-JLS for brevity. Each state of the…

系统与控制 · 电气工程与系统科学 2020-01-06 Bo Wu , Murat Cubuktepe , Franck Djeumou , Zhe Xu , Ufuk Topcu

A basic model in sequential decision making is the Markov decision process (MDP), which is extended to Robust MDPs (RMDPs) by allowing uncertainty in transition probabilities and optimizing against the worst-case transition probabilities…

计算复杂性 · 计算机科学 2026-05-11 Ali Asadi , Krishnendu Chatterjee , Alipasha Montaseri , Ali Shafiee

We present new algorithms for computing and approximating bisimulation metrics in Markov Decision Processes (MDPs). Bisimulation metrics are an elegant formalism that capture behavioral equivalence between states and provide strong…

机器学习 · 计算机科学 2019-11-22 Pablo Samuel Castro

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 POMDP whose observation function is a missingness function,…

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 belong to a so-called uncertainty set, for instance in the form…

最优化与控制 · 数学 2020-01-24 Marnix Suilen , Nils Jansen , Murat Cubuktepe , Ufuk Topcu

We consider two core algorithmic problems for probabilistic verification: the maximal end-component decomposition and the almost-sure reachability set computation for Markov decision processes (MDPs). For MDPs with treewidth $k$, we present…

数据结构与算法 · 计算机科学 2016-08-11 Krishnendu Chatterjee , Jakub Łącki

We study planning problems where autonomous agents operate inside environments that are subject to uncertainties and not fully observable. Partially observable Markov decision processes (POMDPs) are a natural formal model to capture such…

人工智能 · 计算机科学 2018-02-28 Steven Carr , Nils Jansen , Ralf Wimmer , Jie Fu , Ufuk Topcu

We develop a qualitative theory of Markov Decision Processes (MDPs) and Partially Observable MDPs that can be used to model sequential decision making tasks when only qualitative information is available. Our approach is based upon an…

人工智能 · 计算机科学 2013-01-07 Blai Bonet , Judea Pearl

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…

最优化与控制 · 数学 2021-12-24 Xiaoming Duan , Yagiz Savas , Rui Yan , Zhe Xu , Ufuk Topcu

This work addresses the general problem of control synthesis for continuous-space, discrete-time stochastic systems with probabilistic guarantees via finite abstractions. While established methods exist, they often trade off accuracy for…

系统与控制 · 电气工程与系统科学 2025-07-04 Ibon Gracia , Morteza Lahijanian

Markov decision processes (MDPs) are the defacto frame-work for sequential decision making in the presence ofstochastic uncertainty. A classical optimization criterion forMDPs is to maximize the expected discounted-sum pay-off, which…

人工智能 · 计算机科学 2020-02-28 Tomas Brazdil , Krishnendu Chatterjee , Petr Novotny , Jiri Vahala

This paper considers the permissive supervisor synthesis for probabilistic systems modeled as Markov Decision Processes (MDP). Such systems are prevalent in power grids, transportation networks, communication networks and robotics. Unlike…

计算机科学中的逻辑 · 计算机科学 2017-03-23 Bo Wu , Xiaobin Zhang , Hai Lin

Partially observable Markov decision processes (POMDPs) are widely used in probabilistic planning problems in which an agent interacts with an environment using noisy and imprecise sensors. We study a setting in which the sensors are only…

人工智能 · 计算机科学 2017-10-03 Krishnendu Chatterjee , Martin Chmelik , Ufuk Topcu

Software-intensive systems, such as software product lines and robotics, utilise Markov decision processes (MDPs) to capture uncertainty and analyse sequential decision-making problems. Despite the usefulness of conventional policy…

人工智能 · 计算机科学 2026-05-01 Alexandros Evangelidis , Gricel Vázquez , Simos Gerasimou