English
Related papers

Related papers: Relative Divergence and Maximum Relative Divergenc…

200 papers

In this paper, we focus on the problem of robustifying reinforcement learning (RL) algorithms with respect to model uncertainties. Indeed, in the framework of model-based RL, we propose to merge the theory of constrained Markov decision…

Machine Learning · Computer Science 2020-10-13 Reazul Hasan Russel , Mouhacine Benosman , Jeroen Van Baar

Robust Ordinal Regression (ROR) is a way of dealing with Multiple Criteria Decision Aiding (MCDA), by considering all sets of parameters of an assumed preference model, that are compatible with preference information given by the Decision…

Optimization and Control · Mathematics 2012-06-28 Salvatore Corrente , Salvatore Greco , Roman Slowinski

Standard Markov decision process (MDP) and reinforcement learning algorithms optimize the policy with respect to the expected gain. We propose an algorithm which enables to optimize an alternative objective: the probability that the gain is…

Machine Learning · Computer Science 2023-03-06 Vincent Corlay , Jean-Christophe Sibel

The Moderate Deviations Principle (MDP) is well-understood for sums of independent random variables, worse understood for stationary random sequences, and scantily understood for random fields. An upper bound for a new class of random…

Probability · Mathematics 2018-10-16 Boris Tsirelson

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

Markov decision processes capture sequential decision making under uncertainty, where an agent must choose actions so as to optimize long term reward. The paper studies efficient reasoning mechanisms for Relational Markov Decision Processes…

Artificial Intelligence · Computer Science 2011-11-02 Chenggang Wang , Saket Joshi , Roni Khardon

Markov decision processes (MDPs) is viewed as an optimization of an objective function over certain linear operators over general function spaces. A new existence result is established for the existence of optimal policies in general MDPs,…

Machine Learning · Computer Science 2026-04-01 Abhishek Gupta , Aditya Mahajan

This is basically a polished presentation for Sections 1,2 of arXiv:0801.1050. The Moderate Deviations Principle (MDP) is well-understood for sums of independent random variables, worse understood for stationary random sequences, and…

Probability · Mathematics 2016-12-28 Boris Tsirelson

The joint nonanticipative rate distortion function (NRDF) for a tuple of random processes with individual fidelity criteria is considered. Structural properties of optimal test channel distributions are derived. Further, for the application…

Information Theory · Computer Science 2021-03-31 Charalambos D. Charalambous , Evagoras Stylianou

While most approaches to the problem of Inverse Reinforcement Learning (IRL) focus on estimating a reward function that best explains an expert agent's policy or demonstrated behavior on a control task, it is often the case that such…

Machine Learning · Computer Science 2020-05-01 Dexter R. R. Scobee , S. Shankar Sastry

A wide variety of queueing systems can be naturally modeled as infinite-state Markov Decision Processes (MDPs). In the reinforcement learning (RL) context, a variety of algorithms have been developed to learn and optimize these MDPs. At the…

Machine Learning · Computer Science 2025-07-14 Isaac Grosof , Siva Theja Maguluri , R. Srikant

This paper investigates model robustness in reinforcement learning (RL) to reduce the sim-to-real gap in practice. We adopt the framework of distributionally robust Markov decision processes (RMDPs), aimed at learning a policy that…

Machine Learning · Computer Science 2025-09-09 Laixi Shi , Gen Li , Yuting Wei , Yuxin Chen , Matthieu Geist , Yuejie Chi

Reward finetuning has emerged as a promising approach to aligning foundation models with downstream objectives. Remarkable success has been achieved in the language domain by using reinforcement learning (RL) to maximize rewards that…

Machine Learning · Computer Science 2024-03-29 Fei Deng , Qifei Wang , Wei Wei , Matthias Grundmann , Tingbo Hou

This paper is devoted to first-order algorithms for smooth convex optimization with inexact gradients. Unlike the majority of the literature on this topic, we consider the setting of relative rather than absolute inexactness. More…

Optimization and Control · Mathematics 2023-10-03 Nikita Kornilov , Eduard Gorbunov , Mohammad Alkousa , Fedor Stonyakin , Pavel Dvurechensky , Alexander Gasnikov

We establish the Level-1 and Level-3 Large Deviation Principles (LDPs) for invariant measures on shift spaces over finite alphabets under very general decoupling conditions for which the thermodynamic formalism does not apply. Such…

Mathematical Physics · Physics 2019-06-28 Noé Cuneo , Vojkan Jakšić , Claude-Alain Pillet , Armen Shirikyan

The goal of this paper is to study the Moderate Deviation Principle (MDP) for a system of stochastic reaction-diffusion equations with a time-scale separation in slow and fast components and small noise in the slow component. Based on weak…

Probability · Mathematics 2022-02-03 Ioannis Gasteratos , Michael Salins , Konstantinos Spiliopoulos

Various algorithms for reinforcement learning (RL) exhibit dramatic variation in their convergence rates as a function of problem structure. Such problem-dependent behavior is not captured by worst-case analyses and has accordingly inspired…

Machine Learning · Statistics 2022-01-24 Koulik Khamaru , Eric Xia , Martin J. Wainwright , Michael I. Jordan

We consider deterministic Markov decision processes (MDPs) and apply max-plus algebra tools to approximate the value iteration algorithm by a smaller-dimensional iteration based on a representation on dictionaries of value functions. The…

Machine Learning · Computer Science 2019-06-21 Francis Bach

Robust Markov Decision Processes (RMDPs) have recently been recognized as a valuable and promising approach to discovering a policy with creditable performance, particularly in the presence of a dynamic environment and estimation errors in…

Optimization and Control · Mathematics 2024-06-04 Zhenwei Lin , Chenyu Xue , Qi Deng , Yinyu Ye

Partially Observable Markov Decision Processes (POMDPs) can model complex sequential decision-making problems under stochastic and uncertain environments. A main reason hindering their broad adoption in real-world applications is the lack…