中文
相关论文

相关论文: Tight Performance Bounds for Approximate Modified …

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 consider the infinite-horizon discounted optimal control problem formalized by Markov Decision Processes. We focus on several approximate variations of the Policy Iteration algorithm: Approximate Policy Iteration, Conservative Policy…

人工智能 · 计算机科学 2014-05-13 Bruno Scherrer

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 consider the infinite-horizon discounted optimal control problem formalized by Markov Decision Processes. We focus on Policy Search algorithms, that compute an approximately optimal policy by following the standard Policy Iteration (PI)…

人工智能 · 计算机科学 2013-06-04 Bruno Scherrer

We consider approximate dynamic programming in $\gamma$-discounted Markov decision processes and apply it to approximate planning with linear value-function approximation. Our first contribution is a new variant of Approximate Policy…

机器学习 · 计算机科学 2022-10-31 Gellért Weisz , András György , Tadashi Kozuno , Csaba Szepesvári

In this paper, we propose a novel policy iteration method, called dynamic policy programming (DPP), to estimate the optimal policy in the infinite-horizon Markov decision processes. We prove the finite-iteration and asymptotic l\infty-norm…

机器学习 · 计算机科学 2011-09-09 Mohammad Gheshlaghi Azar , Vicenc Gomez , Hilbert J. Kappen

We consider a dynamic programming (DP) approach to approximately solving an infinite-horizon constrained Markov decision process (CMDP) problem with a fixed initial-state for the expected total discounted-reward criterion with a…

最优化与控制 · 数学 2023-08-08 Hyeong Soo Chang

We consider the problem of designing a control policy for an infinite-horizon discounted cost Markov decision process $\mathcal{M}$ when we only have access to an approximate model $\hat{\mathcal{M}}$. How well does an optimal policy…

最优化与控制 · 数学 2024-02-15 Berk Bozkurt , Aditya Mahajan , Ashutosh Nayyar , Yi Ouyang

This paper studies the approximation of optimal control policies by quantized (discretized) policies for a very general class of Markov decision processes (MDPs). The problem is motivated by applications in networked control systems,…

最优化与控制 · 数学 2015-05-14 Naci Saldi , Serdar Yüksel , Tamás Linder

Modified policy iteration (MPI) is a dynamic programming (DP) algorithm that contains the two celebrated policy and value iteration methods. Despite its generality, MPI has not been thoroughly studied, especially its approximation form…

人工智能 · 计算机科学 2012-05-21 Bruno Scherrer , Victor Gabillon , Mohammad Ghavamzadeh , Matthieu Geist

We study the synthesis of a policy in a Markov decision process (MDP) following which an agent reaches a target state in the MDP while minimizing its total discounted cost. The problem combines a reachability criterion with a discounted…

最优化与控制 · 数学 2021-03-18 Yagiz Savas , Christos K. Verginis , Michael Hibbard , Ufuk Topcu

We investigate the problem of best policy identification in discounted linear Markov Decision Processes in the fixed confidence setting under a generative model. We first derive an instance-specific lower bound on the expected number of…

机器学习 · 计算机科学 2022-08-12 Jerome Taupin , Yassir Jedra , Alexandre Proutiere

Algorithms developed under stationary Markov Decision Processes (MDPs) often face challenges in non-stationary environments, and infinite-horizon formulations may not directly apply to finite-horizon tasks. To address these limitations, we…

机器学习 · 计算机科学 2025-12-03 Zhizuo Chen , Theodore T. Allen

This note provides upper bounds on the number of operations required to compute by value iterations a nearly optimal policy for an infinite-horizon discounted Markov decision process with a finite number of states and actions. For a given…

最优化与控制 · 数学 2020-01-29 Eugene A. Feinberg , Gaojin He

We present the first finite time global convergence analysis of policy gradient in the context of infinite horizon average reward Markov decision processes (MDPs). Specifically, we focus on ergodic tabular MDPs with finite state and action…

机器学习 · 计算机科学 2024-03-12 Navdeep Kumar , Yashaswini Murthy , Itai Shufaro , Kfir Y. Levy , R. Srikant , Shie Mannor

In this paper, we show how a simulated Markov decision process (MDP) built by the so-called \emph{baseline} policies, can be used to compute a different policy, namely the \emph{simulated optimal} policy, for which the performance of this…

最优化与控制 · 数学 2014-10-13 Yinlam Chow , Mohammad Ghavamzadeh

In this paper, we study a mean-variance optimization problem in an infinite horizon discrete time discounted Markov decision process (MDP). The objective is to minimize the variance of system rewards with the constraint of mean performance.…

最优化与控制 · 数学 2017-08-24 Li Xia

This article presents a constrained policy optimization approach for the optimal control of systems under nonstationary uncertainties. We introduce an assumption that we call Markov embeddability that allows us to cast the stochastic…

最优化与控制 · 数学 2026-05-11 Sungho Shin , François Pacaud , Emil Contantinescu , Mihai Anitescu

Most reinforcement learning methods are based upon the key assumption that the transition dynamics and reward functions are fixed, that is, the underlying Markov decision process is stationary. However, in many real-world applications, this…

机器学习 · 计算机科学 2020-09-23 Yash Chandak , Georgios Theocharous , Shiv Shankar , Martha White , Sridhar Mahadevan , Philip S. Thomas

Approximate dynamic programming is a popular method for solving large Markov decision processes. This paper describes a new class of approximate dynamic programming (ADP) methods- distributionally robust ADP-that address the curse of…

机器学习 · 统计学 2012-05-22 Marek Petrik
‹ 上一页 1 2 3 10 下一页 ›