中文
相关论文

相关论文: Markov Decision Processes of the Third Kind: Learn…

200 篇论文

In this paper, we present an online reinforcement learning algorithm for constrained Markov decision processes with a safety constraint. Despite the necessary attention of the scientific community, considering stochastic stopping time, the…

机器学习 · 计算机科学 2024-03-26 Abhijit Mazumdar , Rafal Wisniewski , Manuela L. Bujorianu

In this paper, we propose a stochastic search algorithm for solving general optimization problems with little structure. The algorithm iteratively finds high quality solutions by randomly sampling candidate solutions from a parameterized…

最优化与控制 · 数学 2013-01-08 Enlu Zhou , Jiaqiao Hu

This paper studies an infinite horizon optimal control problem for discrete-time linear system and quadratic criteria, both with random parameters which are independent and identically distributed with respect to time. In this general…

最优化与控制 · 数学 2024-03-04 Deyue Li

We consider a piecewise deterministic Markov decision process, where the expected exponential utility of total (nonnegative) cost is to be minimized. The cost rate, transition rate and post-jump distributions are under control. The state…

最优化与控制 · 数学 2017-11-22 Xin Guo , Yi Zhang

The main goal of this paper is to investigate continuous-time distributed dynamic programming (DP) algorithms for networked multi-agent Markov decision problems (MAMDPs). In our study, we adopt a distributed multi-agent framework where…

系统与控制 · 电气工程与系统科学 2024-06-14 Donghwan Lee , Han-Dong Lim , Do Wan Kim

Markov Decision Processes are classically solved using Value Iteration and Policy Iteration algorithms. Recent interest in Reinforcement Learning has motivated the study of methods inspired by optimization, such as gradient ascent. Among…

机器学习 · 计算机科学 2021-05-05 Sajad Khodadadian , Prakirt Raj Jhunjhunwala , Sushil Mahavir Varma , Siva Theja Maguluri

We present a case study applying learning-based distributionally robust model predictive control to highway motion planning under stochastic uncertainty of the lane change behavior of surrounding road users. The dynamics of road users are…

系统与控制 · 电气工程与系统科学 2022-11-08 Mathijs Schuurmans , Alexander Katriniok , Christopher Meissen , H. Eric Tseng , Panagiotis Patrinos

This paper studies the networked multi-agent reinforcement learning (NMARL) problem, where the objective of agents is to collaboratively maximize the discounted average cumulative rewards. Different from the existing methods that suffer…

多智能体系统 · 计算机科学 2025-06-02 Pengcheng Dai , Yuanqiu Mo , Wenwu Yu , Wei Ren

Many real-world decision-making problems face the off-dynamics challenge: the agent learns a policy in a source domain and deploys it in a target domain with different state transitions. The distributionally robust Markov decision process…

机器学习 · 计算机科学 2025-05-26 Zhishuai Liu , Pan Xu

Decision-making under distribution shift is a central challenge in reinforcement learning (RL), where training and deployment environments differ. We study this problem through the lens of robust Markov decision processes (RMDPs), which…

机器学习 · 计算机科学 2025-10-17 Jingwen Gu , Yiting He , Zhishuai Liu , Pan Xu

Safety is an essential requirement for reinforcement learning systems. The newly emerging framework of robust constrained Markov decision processes allows learning policies that satisfy long-term constraints while providing guarantees under…

机器学习 · 计算机科学 2025-12-19 David M. Bossens , Atsushi Nitanda

Three major challenges in reinforcement learning are the complex dynamical systems with large state spaces, the costly data acquisition processes, and the deviation of real-world dynamics from the training environment deployment. To…

机器学习 · 计算机科学 2024-06-04 Shyam Sundhar Ramesh , Pier Giuseppe Sessa , Yifan Hu , Andreas Krause , Ilija Bogunovic

Motivated by emerging applications in machine learning, we consider an optimization problem in a general form where the gradient of the objective function is available through a biased stochastic oracle. We assume a bias-control parameter…

最优化与控制 · 数学 2026-02-10 Yin Liu , Sam Davanloo Tajbakhsh

Stochastic optimal control problems have a long tradition in applied probability, with the questions addressed being of high relevance in a multitude of fields. Even though theoretical solutions are well understood in many scenarios, their…

统计理论 · 数学 2024-05-28 Sören Christensen , Claudia Strauch , Lukas Trottner

Learning in games provides a powerful framework to design control policies for self-interested agents that may be coupled through their dynamics, costs, or constraints. We consider the case where the dynamics of the coupled system can be…

系统与控制 · 电气工程与系统科学 2024-09-18 Mostafa M. Shibl , Vijay Gupta

Controllable Markov chains describe the dynamics of sequential decision making tasks and are the central component in optimal control and reinforcement learning. In this work, we give the general form of an optimal policy for learning…

机器学习 · 计算机科学 2025-12-24 Peter N. Loxley

In this paper, we consider Markov Decision Processes (MDPs) with error states. Error states are those states entering which is undesirable or dangerous. We define the risk with respect to a policy as the probability of entering such a state…

机器学习 · 计算机科学 2011-09-13 P. Geibel , F. Wysotzki

We consider a hidden Markov model with multiple observation processes, one of which is chosen at each point in time by a policy---a deterministic function of the information state---and attempt to determine which policy minimises the…

概率论 · 数学 2015-03-17 James Y. Zhao

Markov decision processes (MDPs) are a popular model for performance analysis and optimization of stochastic systems. The parameters of stochastic behavior of MDPs are estimates from empirical observations of a system; their values are not…

人工智能 · 计算机科学 2017-10-26 Dimitri Scheftelowitsch , Peter Buchholz , Vahid Hashemi , Holger Hermanns

Many real-world problems require trading off multiple competing objectives. However, these objectives are often in different units and/or scales, which can make it challenging for practitioners to express numerical preferences over…