English
Related papers

Related papers: Reoptimization Nearly Solves Weakly Coupled Markov…

200 papers

We study computationally and statistically efficient reinforcement learning under the linear $Q^{\pi}$ realizability assumption, where any policy's $Q$-function is linear in a given state-action feature representation. Prior methods in this…

Machine Learning · Computer Science 2026-03-03 Yijing Ke , Zihan Zhang , Ruosong Wang

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…

Machine Learning · Computer Science 2022-10-31 Gellért Weisz , András György , Tadashi Kozuno , Csaba Szepesvári

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,…

Machine Learning · Computer Science 2022-02-02 Liyu Chen , Rahul Jain , Haipeng Luo

We consider restless multi-armed bandit (RMAB) with a finite horizon and multiple pulls per period. Leveraging the Lagrangian relaxation, we approximate the problem with a collection of single arm problems. We then propose an index-based…

Optimization and Control · Mathematics 2017-07-04 Weici Hu , Peter Frazier

A renewal system divides the slotted timeline into back to back time periods called renewal frames. At the beginning of each frame, it chooses a policy from a set of options for that frame. The policy determines the duration of the frame,…

Optimization and Control · Mathematics 2021-02-02 Xiaohan Wei

Memoryless and finite-memory policies offer a practical alternative for solving partially observable Markov decision processes (POMDPs), as they operate directly in the output space rather than in the high-dimensional belief space. However,…

Machine Learning · Computer Science 2025-12-15 Roy van Zuijlen , Duarte Antunes

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…

Computational Complexity · Computer Science 2026-05-11 Ali Asadi , Krishnendu Chatterjee , Alipasha Montaseri , Ali Shafiee

A more general formulation of the linear bandit problem is considered to allow for dependencies over time. Specifically, it is assumed that there exists an unknown $\mathbb{R}^d$-valued stationary $\varphi$-mixing sequence of parameters…

Machine Learning · Statistics 2024-05-20 Azadeh Khaleghi

Policy Mirror Descent (PMD) stands as a versatile algorithmic framework encompassing several seminal policy gradient algorithms such as natural policy gradient, with connections with state-of-the-art reinforcement learning (RL) algorithms…

Machine Learning · Computer Science 2024-11-07 Kimon Protopapas , Anas Barakat

Offline reinforcement learning (RL) aims at learning an optimal strategy using a pre-collected dataset without further interactions with the environment. While various algorithms have been proposed for offline RL in the previous literature,…

Machine Learning · Computer Science 2023-03-02 Wei Xiong , Han Zhong , Chengshuai Shi , Cong Shen , Liwei Wang , Tong Zhang

We introduce \texttt{OPO-CMDP}, the first policy optimization algorithm for stochastic Contextual Markov Decision Process (CMDPs) under general offline function approximation. Our approach achieves a high probability regret bound of…

Machine Learning · Computer Science 2026-02-17 Orin Levy , Aviv Rosenberg , Alon Cohen , Yishay Mansour

This paper describes a novel method to solve average-reward semi-Markov decision processes, by reducing them to a minimal sequence of cumulative reward problems. The usual solution methods for this type of problems update the gain (optimal…

Machine Learning · Computer Science 2015-04-21 Reinaldo Uribe Muriel , Fernando Lozando , Charles Anderson

We develop a stochastic approximation-type algorithm to solve finite state/action, infinite-horizon, risk-aware Markov decision processes. Our algorithm has two loops. The inner loop computes the risk by solving a stochastic saddle-point…

Optimization and Control · Mathematics 2019-12-05 Wenjie Huang , William B. Haskell

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…

Systems and Control · Electrical Eng. & Systems 2025-09-04 Zixuan He , Charalambos D. Charalambous , Photios A. Stavrou

We study a finite-horizon restless multi-armed bandit problem with multiple actions, dubbed R(MA)^2B. The state of each arm evolves according to a controlled Markov decision process (MDP), and the reward of pulling an arm depends on both…

Machine Learning · Computer Science 2022-03-25 Guojun Xiong , Jian Li , Rahul Singh

Restless bandit problems are instances of non-stationary multi-armed bandits. These problems have been studied well from the optimization perspective, where the goal is to efficiently find a near-optimal policy when system parameters are…

Machine Learning · Computer Science 2019-10-29 Young Hun Jung , Ambuj Tewari

We introduce a bandit framework for stochastic matching under the multinomial logit (MNL) choice model. In our setting, $N$ agents on one side are assigned to $K$ arms on the other side, where each arm stochastically selects an agent from…

Machine Learning · Statistics 2026-01-30 Jung-hun Kim , Min-hwan Oh

We consider discounted infinite-horizon constrained Markov decision processes (CMDPs), where the goal is to find an optimal policy that maximizes the expected cumulative reward while satisfying expected cumulative constraints. Motivated by…

Machine Learning · Computer Science 2025-03-04 Tingting Ni , Maryam Kamgarpour

We study the problem of learning optimal policies in finite-horizon Markov Decision Processes (MDPs) using low-rank reinforcement learning (RL) methods. In finite-horizon MDPs, the policies, and therefore the value functions (VFs) are not…

Machine Learning · Computer Science 2026-05-14 Sergio Rozada , Jose Luis Orejuela , Antonio G. Marques

We investigate the classical active pure exploration problem in Markov Decision Processes, where the agent sequentially selects actions and, from the resulting system trajectory, aims at identifying the best policy as fast as possible. We…

Machine Learning · Statistics 2021-10-26 Aymen Al Marjani , Aurélien Garivier , Alexandre Proutiere