English
Related papers

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

200 papers

In this paper, we study safe data collection for the purpose of policy evaluation in tabular Markov decision processes (MDPs). In policy evaluation, we are given a \textit{target} policy and asked to estimate the expected cumulative reward…

Machine Learning · Computer Science 2024-06-05 Subhojyoti Mukherjee , Josiah P. Hanna , Robert Nowak

Practical reinforcement learning problems are often formulated as constrained Markov decision process (CMDP) problems, in which the agent has to maximize the expected return while satisfying a set of prescribed safety constraints. In this…

Machine Learning · Computer Science 2019-09-23 Shin-ichi Maeda , Hayato Watahiki , Shintarou Okada , Masanori Koyama

We study the off-policy evaluation (OPE) problem in reinforcement learning with linear function approximation, which aims to estimate the value function of a target policy based on the offline data collected by a behavior policy. We propose…

Machine Learning · Computer Science 2022-01-05 Yifei Min , Tianhao Wang , Dongruo Zhou , Quanquan Gu

Variable selection is fundamental to high-dimensional statistical modeling. Many variable selection techniques may be implemented by maximum penalized likelihood using various penalty functions. Optimizing the penalized likelihood function…

Statistics Theory · Mathematics 2007-06-13 David R. Hunter , Runze Li

In the Markov decision process model, policies are usually evaluated by expected cumulative rewards. As this decision criterion is not always suitable, we propose in this paper an algorithm for computing a policy optimal for the quantile…

Artificial Intelligence · Computer Science 2016-12-02 Hugo Gilbert , Paul Weng , Yan Xu

While there is an extensive body of research on the analysis of Value Iteration (VI) for discounted cumulative-reward MDPs, prior work on analyzing VI for (undiscounted) average-reward MDPs has been limited, and most prior results focus on…

Optimization and Control · Mathematics 2026-02-10 Jongmin Lee , Ernest K. Ryu

We study offline reinforcement learning problems with a long-run average reward objective. The state-action pairs generated by any fixed behavioral policy thus follow a Markov chain, and the {\em empirical} state-action-next-state…

Optimization and Control · Mathematics 2025-03-18 Mengmeng Li , Daniel Kuhn , Tobias Sutter

There exist a number of reinforcement learning algorithms which learnby climbing the gradient of expected reward. Their long-runconvergence has been proved, even in partially observableenvironments with non-deterministic actions, and…

Machine Learning · Computer Science 2013-01-14 Lex Weaver , Nigel Tao

Autonomous agents optimize the reward function we give them. What they don't know is how hard it is for us to design a reward function that actually captures what we want. When designing the reward, we might think of some specific training…

Artificial Intelligence · Computer Science 2020-10-08 Dylan Hadfield-Menell , Smitha Milli , Pieter Abbeel , Stuart Russell , Anca Dragan

In several applications such as clinical trials and financial portfolio optimization, the expected value (or the average reward) does not satisfactorily capture the merits of a drug or a portfolio. In such applications, risk plays a crucial…

Machine Learning · Statistics 2022-05-13 Vincent Y. F. Tan , Prashanth L. A. , Krishna Jagannathan

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…

Machine Learning · Computer Science 2011-09-13 P. Geibel , F. Wysotzki

We study countably infinite Markov decision processes (MDPs) with real-valued transition rewards. Every infinite run induces the following sequences of payoffs: 1. Point payoff (the sequence of directly seen transition rewards), 2. Mean…

Computational Complexity · Computer Science 2023-06-22 Richard Mayr , Eric Munday

We consider reinforcement learning (RL) in Markov Decision Processes in which an agent repeatedly interacts with an environment that is modeled by a controlled Markov process. At each time step $t$, it earns a reward, and also incurs a…

Machine Learning · Computer Science 2023-03-16 Rahul Singh , Abhishek Gupta , Ness B. Shroff

We study the sample complexity of the plug-in approach for learning $\varepsilon$-optimal policies in average-reward Markov decision processes (MDPs) with a generative model. The plug-in approach constructs a model estimate then computes an…

Machine Learning · Computer Science 2025-02-12 Matthew Zurek , Yudong Chen

This paper studies optimization of Conditional Value-at-Risk (CVaR) for Markov Decision Processes (MDPs) with finite state and action sets. It introduces the Dynamically augmented CVaR (DCVaR) risk measure and provides an algorithm for its…

Optimization and Control · Mathematics 2026-03-12 Eugene A. Feinberg , Rui Ding

Reinforcement Learning aims at identifying and evaluating efficient control policies from data. In many real-world applications, the learner is not allowed to experiment and cannot gather data in an online manner (this is the case when…

Machine Learning · Computer Science 2024-07-02 Daniele Foffano , Alessio Russo , Alexandre Proutiere

The goal of this paper is to analyze distributional Markov Decision Processes as a class of control problems in which the objective is to learn policies that steer the distribution of a cumulative reward toward a prescribed target law,…

Optimization and Control · Mathematics 2026-02-09 Nicole Bäuerle , Athanasios Vasileiadis

For decades, National Football League (NFL) coaches' observed fourth down decisions have been largely inconsistent with prescriptions based on statistical models. In this paper, we develop a framework to explain this discrepancy using an…

Applications · Statistics 2026-03-06 Nathan Sandholtz , Lucas Wu , Martin Puterman , Timothy C. Y. Chan

We investigate an infinite-horizon average reward Markov Decision Process (MDP) with delayed, composite, and partially anonymous reward feedback. The delay and compositeness of rewards mean that rewards generated as a result of taking an…

Machine Learning · Computer Science 2023-08-29 Washim Uddin Mondal , Vaneet Aggarwal

We study the minimization of a spectral risk measure of the total discounted cost generated by a Markov Decision Process (MDP) over a finite or infinite planning horizon. The MDP is assumed to have Borel state and action spaces and the cost…

Optimization and Control · Mathematics 2025-10-16 Nicole Bäuerle , Alexander Glauner
‹ Prev 1 8 9 10 Next ›