中文
相关论文

相关论文: Fast Approximate Dynamic Programming for Infinite-…

200 篇论文

We consider infinite-horizon $\gamma$-discounted Markov Decision Processes, for which it is known that there exists a stationary optimal policy. We consider the algorithm Value Iteration and the sequence of policies $\pi_1,...,\pi_k$ it…

人工智能 · 计算机科学 2012-04-02 Bruno Scherrer

We study the computational complexity of the infinite-horizon discounted-reward Markov Decision Problem (MDP) with a finite state space $|\mathcal{S}|$ and a finite action space $|\mathcal{A}|$. We show that any randomized algorithm needs a…

计算复杂性 · 计算机科学 2017-05-24 Yichen Chen , Mengdi Wang

In this paper, we consider the finite-state approximation of a discrete-time constrained Markov decision process (MDP) under the discounted and average cost criteria. Using the linear programming formulation of the constrained discounted…

最优化与控制 · 数学 2018-07-10 Naci Saldi

We consider the problem of optimally designing a system for repeated use under uncertainty. We develop a modeling framework that integrates design and operational phases, which are represented by a mixed-integer program and discounted-cost…

最优化与控制 · 数学 2024-03-25 Seth Brown , Saumya Sinha , Andrew J Schaefer

We consider approximate dynamic programming for the infinite-horizon stationary $\gamma$-discounted optimal control problem formalized by Markov Decision Processes. While in the exact case it is known that there always exists an optimal…

最优化与控制 · 数学 2013-04-23 Boris Lesner , Bruno Scherrer

This paper studies a discrete-time optimal switching problem on a finite horizon. The underlying model has a running reward, terminal reward and signed (positive and negative) switching costs. Using the martingale approach to optimal…

最优化与控制 · 数学 2016-10-17 Randall Martyr

We investigate planning in time-critical domains represented as Markov Decision Processes, showing that search based techniques can be a very powerful method for finding close to optimal plans. To reduce the computational cost of planning…

人工智能 · 计算机科学 2013-02-28 Richard Dearden , Craig Boutilier

This note re-visits the rolling-horizon control approach to the problem of a Markov decision process (MDP) with infinite-horizon discounted expected reward criterion. Distinguished from the classical value-iteration approach, we develop an…

最优化与控制 · 数学 2022-06-07 Hyeong Soo Chang

Many real-world applications, such as those in medical domains, recommendation systems, etc, can be formulated as large state space reinforcement learning problems with only a small budget of the number of policy changes, i.e., low…

机器学习 · 计算机科学 2021-01-05 Minbo Gao , Tianle Xie , Simon S. Du , Lin F. Yang

We study the problem of reinforcement learning in infinite-horizon discounted linear Markov decision processes (MDPs), and propose the first computationally efficient algorithm achieving rate-optimal regret guarantees in this setting. Our…

机器学习 · 计算机科学 2026-03-16 Antoine Moulin , Gergely Neu , Luca Viano

We propose a vector linear programming formulation for a non-stationary, finite-horizon Markov decision process with vector-valued rewards. Pareto efficient policies are shown to correspond to efficient solutions of the linear program, and…

最优化与控制 · 数学 2025-06-02 Anas Mifrani , Dominikus Noll

We consider infinite-horizon stationary $\gamma$-discounted Markov Decision Processes, for which it is known that there exists a stationary optimal policy. Using Value and Policy Iteration with some error $\epsilon$ at each iteration, it is…

机器学习 · 计算机科学 2012-11-30 Bruno Scherrer , Boris Lesner

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…

机器学习 · 计算机科学 2025-04-17 Kihyuk Hong , Ambuj Tewari

We study regret minimization for infinite-horizon average-reward Markov Decision Processes (MDPs) under cost constraints. We start by designing a policy optimization algorithm with carefully designed action-value estimator and bonus term,…

机器学习 · 计算机科学 2022-02-02 Liyu Chen , Rahul Jain , Haipeng Luo

Predictive control is frequently used for control problems involving constraints. Being an optimization based technique utilizing a user specified so-called stage cost, performance properties, i.e., bounds on the infinite horizon…

系统与控制 · 电气工程与系统科学 2022-09-09 Lukas Beckenbach , Stefan Streif

This paper studies a finite-horizon Markov decision problem with information-theoretic constraints, where the goal is to minimize directed information from the controlled source process to the control process, subject to stage-wise cost…

系统与控制 · 电气工程与系统科学 2025-09-04 Zixuan He , Charalambos D. Charalambous , Photios A. Stavrou

We present an efficient algorithm to compute the induced norms of finite-horizon Linear Time-Varying (LTV) systems. The formulation includes both induced $\mathcal{L}_2$ and terminal Euclidean norm penalties. Existing computational…

系统与控制 · 电气工程与系统科学 2020-11-03 Jyot Buch , Murat Arcak , Peter Seiler

We use one-step conditional risk mappings to formulate a risk averse version of a total cost problem on a controlled Markov process in discrete time infinite horizon. The nonnegative one step costs are assumed to be lower semi-continuous…

最优化与控制 · 数学 2018-06-05 Kerem Ugurlu

This paper studies value iteration for infinite horizon contracting Markov decision processes under convexity assumptions and when the state space is uncountable. The original value iteration is replaced with a more tractable form and the…

最优化与控制 · 数学 2018-02-21 Jeremy Yee

We consider the task of designing sparse control laws for large-scale systems by directly minimizing an infinite horizon quadratic cost with an $\ell_1$ penalty on the feedback controller gains. Our focus is on an improved algorithm that…

最优化与控制 · 数学 2013-12-18 Matt Wytock , J. Zico Kolter