English
Related papers

Related papers: Risk-averse optimization of total rewards in Marko…

200 papers

In this paper, we consider risk-sensitive Markov Decision Processes (MDPs) with Borel state and action spaces and unbounded cost under both finite and infinite planning horizons. Our optimality criterion is based on the recursive…

Optimization and Control · Mathematics 2025-10-16 Nicole Bäuerle , Alexander Glauner

We consider finite horizon Markov decision processes under performance measures that involve both the mean and the variance of the cumulative reward. We show that either randomized or history-based policies can improve performance. We prove…

Machine Learning · Computer Science 2011-05-02 Shie Mannor , John Tsitsiklis

We consider the batch (off-line) policy learning problem in the infinite horizon Markov Decision Process. Motivated by mobile health applications, we focus on learning a policy that maximizes the long-term average reward. We propose a…

Statistics Theory · Mathematics 2022-09-20 Peng Liao , Zhengling Qi , Runzhe Wan , Predrag Klasnja , Susan Murphy

We study a class of infinite-horizon average-cost Markov Decision Processes (MDPs) whose reward and transition structures are nearly separable. For the totally separable baseline (that is, with no perturbation), we derive an explicit…

Optimization and Control · Mathematics 2025-10-28 Dhairya Kantawala

The distributionally robust Markov Decision Process (MDP) approach asks for a distributionally robust policy that achieves the maximal expected total reward under the most adversarial distribution of uncertain parameters. In this paper, we…

Systems and Control · Computer Science 2018-10-10 Zhi Chen , Pengqian Yu , William B. Haskell

We study online learning in episodic constrained Markov decision processes (CMDPs), where the learner aims at collecting as much reward as possible over the episodes, while satisfying some long-term constraints during the learning process.…

This paper considers stochastic-constrained stochastic optimization where the stochastic constraint is to satisfy that the expectation of a random function is below a certain threshold. In particular, we study the setting where data samples…

Optimization and Control · Mathematics 2026-01-27 Yeongjong Kim , Dabeen Lee

Partially Observable Markov Decision Processes (POMDPs) provide an efficient way to model real-world sequential decision making processes. Motivated by the problem of maintenance and inspection of a group of infrastructure components with…

Optimization and Control · Mathematics 2024-08-15 Manav Vora , Pranay Thangeda , Michael N. Grussing , Melkior Ornik

In this paper, we consider a finite-horizon Markov decision process (MDP) for which the objective at each stage is to minimize a quantile-based risk measure (QBRM) of the sequence of future costs; we call the overall objective a dynamic…

Optimization and Control · Mathematics 2017-05-10 Daniel R. Jiang , Warren B. Powell

In this paper, we consider an infinite horizon average reward Markov Decision Process (MDP). Distinguishing itself from existing works within this context, our approach harnesses the power of the general policy gradient-based algorithm,…

Machine Learning · Computer Science 2024-02-06 Qinbo Bai , Washim Uddin Mondal , Vaneet Aggarwal

Average-reward Markov decision processes (MDPs) provide a foundational framework for sequential decision-making under uncertainty. However, average-reward MDPs have remained largely unexplored in reinforcement learning (RL) settings, with…

Machine Learning · Computer Science 2025-08-29 Juan Sebastian Rojas , Chi-Guhn Lee

We study the complexity of central controller synthesis problems for finite-state Markov decision processes, where the objective is to optimize both the expected mean-payoff performance of the system and its stability. We argue that the…

Systems and Control · Computer Science 2013-05-20 Tomáš Brázdil , Krishnendu Chatterjee , Vojtěch Forejt , Antonín Kučera

We consider the problem of maximizing the expected average reward obtained over an infinite time horizon by $n$ weakly coupled Markov decision processes. Our setup is a substantial generalization of the multi-armed restless bandit problem…

Optimization and Control · Mathematics 2026-04-01 Diego Goldsztajn , Konstantin Avrachenkov

We study multi-robot persistent monitoring on weighted graphs, where node weights encode monitoring priorities and edge weights encode travel distances. The goal is to design joint robot trajectories that minimize the worst-case weighted…

Robotics · Computer Science 2026-05-12 Weizhen Wang , Ziheng Wang , Jianping He , Xinping Guan , Xiaoming Duan

We consider non-standard Markov Decision Processes (MDPs) where the target function is not only a simple expectation of the accumulated reward. Instead, we consider rather general functionals of the joint distribution of terminal state and…

Optimization and Control · Mathematics 2025-10-16 Nicole Bäuerle , Tamara Göll , Anna Jaśkiewicz

We propose a new complexity measure for Markov decision processes (MDPs), the maximum expected hitting cost (MEHC). This measure tightens the closely related notion of diameter [JOA10] by accounting for the reward structure. We show that…

Machine Learning · Computer Science 2019-11-06 Falcon Z. Dai , Matthew R. Walter

This paper considers a distributed stochastic optimization problem where the goal is to minimize the time average of a cost function subject to a set of constraints on the time averages of a related stochastic processes called penalties. We…

Information Theory · Computer Science 2016-10-06 B. N. Bharath , Vaishali P

We study distributionally robust Markov games (DR-MGs) with the average-reward criterion, a framework for multi-agent decision-making under uncertainty over extended horizons. In average reward DR-MGs, agents aim to maximize their…

Multiagent Systems · Computer Science 2025-12-12 Zachary Roch , Yue Wang

Repair mechanisms are important within resilient systems to maintain the system in an operational state after an error occurred. Usually, constraints on the repair mechanisms are imposed, e.g., concerning the time or resources required…

Systems and Control · Computer Science 2017-07-12 Christel Baier , Clemens Dubslaff , Ľuboš Korenčiak , Antonín Kučera Vojtěch Řehák

While learning in an unknown Markov Decision Process (MDP), an agent should trade off exploration to discover new information about the MDP, and exploitation of the current knowledge to maximize the reward. Although the agent will…

Machine Learning · Computer Science 2020-07-16 Evrard Garcelon , Mohammad Ghavamzadeh , Alessandro Lazaric , Matteo Pirotta