中文
相关论文

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

200 篇论文

Reinforcement learning consists of finding policies that maximize an expected cumulative long-term reward in a Markov decision process with unknown transition probabilities and instantaneous rewards. In this paper, we consider the problem…

系统与控制 · 计算机科学 2018-07-31 Santiago Paternain , Juan Andrés Bazerque , Austin Small , Alejandro Ribeiro

Stochastic optimal control of dynamical systems is a crucial challenge in sequential decision-making. Recently, control-as-inference approaches have had considerable success, providing a viable risk-sensitive framework to address the…

机器学习 · 计算机科学 2023-12-22 Hany Abdulsamad , Sahel Iqbal , Adrien Corenflos , Simo Särkkä

We consider the problem of controlling a Markov decision process (MDP) with a large state space, so as to minimize average cost. Since it is intractable to compete with the optimal policy for large scale problems, we pursue the more modest…

最优化与控制 · 数学 2014-02-28 Yasin Abbasi-Yadkori , Peter L. Bartlett , Alan Malek

In this paper we build on previous work which uses inferences techniques, in particular Markov Chain Monte Carlo (MCMC) methods, to solve parameterized control problems. We propose a number of modifications in order to make this approach…

机器学习 · 计算机科学 2012-05-14 Matthias Hoffman , Hendrik Kueck , Nando de Freitas , Arnaud Doucet

In dynamic programming and reinforcement learning, the policy for the sequential decision making of an agent in a stochastic environment is usually determined by expressing the goal as a scalar reward function and seeking a policy that…

人工智能 · 计算机科学 2025-02-26 Simon Dima , Simon Fischer , Jobst Heitzig , Joss Oliver

In this article, we discuss two algorithms tailored to discrete-time deterministic finite-horizon nonlinear optimal control problems or so-called deterministic trajectory optimization problems. Both algorithms can be derived from an…

最优化与控制 · 数学 2024-12-10 Mohammad Mahmoudi Filabadi , Tom Lefebvre , Guillaume Crevecoeur

We study discrete-time discounted constrained Markov decision processes (CMDPs) on Borel spaces with unbounded reward functions. In our approach the transition probability functions are weakly or set-wise continuous. The reward functions…

最优化与控制 · 数学 2019-03-29 Eugene A. Feinberg , Anna Jaśkiewicz , Andrzej S. Nowak

Motivated by the post-disaster distribution system restoration problem, in this paper, we study the problem of synthesizing the optimal policy for a Markov Decision Process (MDP) from a sequence of goal sets. For each goal set, our aim is…

系统与控制 · 电气工程与系统科学 2024-04-09 İlker Işık , Onur Yigit Arpali , Ebru Aydin Gol

We revisit the estimation bias in policy gradients for the discounted episodic Markov decision process (MDP) from Deep Reinforcement Learning (DRL) perspective. The objective is formulated theoretically as the expected returns discounted…

机器学习 · 计算机科学 2023-02-13 Haoxuan Pan , Deheng Ye , Xiaoming Duan , Qiang Fu , Wei Yang , Jianping He , Mingfei Sun

We introduce a class of models for multidimensional control problems which we call skip-free Markov decision processes on trees. We describe and analyse an algorithm applicable to Markov decision processes of this type that are skip-free in…

最优化与控制 · 数学 2013-11-11 E. J. Collins

This brief paper presents simple simulation-based algorithms for obtaining an approximately optimal policy in a given finite set in large finite constrained Markov decision processes. The algorithms are adapted from playing strategies for…

最优化与控制 · 数学 2014-12-17 Hyeong Soo Chang

We study reinforcement learning for controlled diffusion processes with unbounded continuous state spaces, bounded continuous actions, and polynomially growing rewards: settings that arise naturally in finance, economics, and operations…

机器学习 · 计算机科学 2025-12-18 Hanqing Jin , Renyuan Xu , Yanzhao Yang

Markov decision processes (MDPs) are used to model a wide variety of applications ranging from game playing over robotics to finance. Their optimal policy typically maximizes the expected sum of rewards given at each step of the decision…

机器学习 · 计算机科学 2025-05-26 Maximilian Nägele , Jan Olle , Thomas Fösel , Remmy Zen , Florian Marquardt

We study a stochastic program where the probability distribution of the uncertain problem parameters is unknown and only indirectly observed via finitely many correlated samples generated by an unknown Markov chain with $d$ states. We…

最优化与控制 · 数学 2021-06-15 Mengmeng Li , Tobias Sutter , Daniel Kuhn

The increasing number of wireless devices operating in unlicensed spectrum motivates the development of intelligent adaptive approaches to spectrum access that go beyond traditional carrier sensing. We develop a novel distributed…

网络与互联网体系结构 · 计算机科学 2021-11-19 Akash Doshi , Jeffrey G. Andrews

Motivated by wide-ranging applications such as video delivery over networks using Multiple Description Codes, congestion control, and inventory management, we study the state-tracking of a Markovian random process with a known transition…

信息论 · 计算机科学 2017-03-06 Parisa Mansourifard , Tara Javidi , Bhaskar Krishnamachari

In this paper, we propose a policy gradient method for confounded partially observable Markov decision processes (POMDPs) with continuous state and observation spaces in the offline setting. We first establish a novel identification result…

机器学习 · 统计学 2023-12-04 Mao Hong , Zhengling Qi , Yanxun Xu

In this paper, we abstract a kind of stochastic processes from evolving processes of growing networks, this process is called growing network Markov chains. Thus the existence and the formulas of degree distribution are transformed to the…

数学物理 · 物理学 2015-05-13 Zhenting Hou , Xiangxing Kong , Dinghua Shi , Guanrong Chen , Qinggui Zhao

Stochastic optimization problems often involve data distributions that change in reaction to the decision variables. This is the case for example when members of the population respond to a deployed classifier by manipulating their features…

最优化与控制 · 数学 2020-12-15 Dmitriy Drusvyatskiy , Lin Xiao

Addressing uncertainty is critical for autonomous systems to robustly adapt to the real world. We formulate the problem of model uncertainty as a continuous Bayes-Adaptive Markov Decision Process (BAMDP), where an agent maintains a…

机器人学 · 计算机科学 2019-05-09 Gilwoo Lee , Brian Hou , Aditya Mandalika , Jeongseok Lee , Sanjiban Choudhury , Siddhartha S. Srinivasa