English
Related papers

Related papers: Sample-Optimal Parametric Q-Learning Using Linearl…

200 papers

We show that one can approximate the least fixed point solution for a multivariate system of monotone probabilistic max(min) polynomial equations, referred to as maxPPSs (and minPPSs, respectively), in time polynomial in both the encoding…

Computational Complexity · Computer Science 2012-02-24 Kousha Etessami , Alistair Stewart , Mihalis Yannakakis

Partially observable Markov decision processes (POMDPs) is a rich mathematical framework that embraces a large class of complex sequential decision-making problems under uncertainty with limited observations. However, the complexity of…

Systems and Control · Electrical Eng. & Systems 2022-11-29 Mingyu Park , Jaeuk Shin , Insoon Yang

We consider a class of optimization problems over stochastic variables where the algorithm can learn information about the value of any variable through a series of costly steps; we model this information acquisition process as a Markov…

Data Structures and Algorithms · Computer Science 2025-07-25 Shuchi Chawla , Dimitris Christou , Amit Harlev , Ziv Scully

In supervised learning, we fit a single statistical model to a given data set, assuming that the data is associated with a singular task, which yields well-tuned models for specific use, but does not adapt well to new contexts. By contrast,…

Machine Learning · Computer Science 2020-09-11 Bingjia Wang , Alec Koppel , Vikram Krishnamurthy

Reinforcement learning algorithms are commonly analyzed (and designed) under the Markov assumption. This is unrealistic, as most environments encountered in practice are either partially observable, or require function approximation that…

Machine Learning · Computer Science 2026-05-28 Onno Eberhard , Claire Vernade , Michael Muehlebach

This dissertation makes three main contributions. First, We identify a new connection between policy gradient and dynamic programming in MMDPs and propose the Coordinate Ascent Dynamic Programming (CADP) algorithm to compute a Markov policy…

Machine Learning · Computer Science 2025-10-21 Xihong Su

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

Reinforcement learning has witnessed recent applications to a variety of tasks in quantum programming. The underlying assumption is that those tasks could be modeled as Markov Decision Processes (MDPs). Here, we investigate the feasibility…

Quantum Physics · Physics 2024-06-06 M. Sohaib Alam , Noah F. Berthusen , Peter P. Orth

Average-reward reinforcement learning offers a principled framework for long-term decision-making by maximizing the mean reward per time step. Although Q-learning is a widely used model-free algorithm with established sample complexity in…

Machine Learning · Statistics 2026-01-21 Yuchen Jiao , Jiin Woo , Gen Li , Gauri Joshi , Yuejie Chi

Offline or batch reinforcement learning seeks to learn a near-optimal policy using history data without active exploration of the environment. To counter the insufficient coverage and sample scarcity of many offline datasets, the principle…

Machine Learning · Computer Science 2022-06-14 Laixi Shi , Gen Li , Yuting Wei , Yuxin Chen , Yuejie Chi

We study the problem of infinite-horizon average-reward reinforcement learning with linear Markov decision processes (MDPs). The associated Bellman operator of the problem not being a contraction makes the algorithm design challenging.…

Machine Learning · Statistics 2025-03-12 Kihyuk Hong , Woojin Chae , Yufan Zhang , Dabeen Lee , Ambuj Tewari

Risk-averse total-reward Markov Decision Processes (MDPs) offer a promising framework for modeling and solving undiscounted infinite-horizon objectives. Existing model-based algorithms for risk measures like the entropic risk measure (ERM)…

Machine Learning · Computer Science 2025-10-27 Xihong Su , Jia Lin Hau , Gersi Doko , Kishan Panaganti , Marek Petrik

In deep reinforcement learning, estimating the value function to evaluate the quality of states and actions is essential. The value function is often trained using the least squares method, which implicitly assumes a Gaussian error…

Machine Learning · Computer Science 2024-03-28 Motoki Omura , Takayuki Osa , Yusuke Mukuta , Tatsuya Harada

We study the statistical limits of Imitation Learning (IL) in episodic Markov Decision Processes (MDPs) with a state space $\mathcal{S}$. We focus on the known-transition setting where the learner is provided a dataset of $N$ length-$H$…

Machine Learning · Computer Science 2021-02-26 Nived Rajaraman , Yanjun Han , Lin F. Yang , Kannan Ramchandran , Jiantao Jiao

We consider a constrained Markov Decision Problem (CMDP) where the goal of an agent is to maximize the expected discounted sum of rewards over an infinite horizon while ensuring that the expected discounted sum of costs exceeds a certain…

Machine Learning · Computer Science 2024-11-01 Washim Uddin Mondal , Vaneet Aggarwal

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

Although actor-critic methods have been successful in practice, their theoretical analyses have several limitations. Specifically, existing theoretical work either sidesteps the exploration problem by making strong assumptions or analyzes…

Machine Learning · Computer Science 2026-04-02 Max Qiushi Lin , Reza Asad , Kevin Tan , Haque Ishfaq , Csaba Szepesvari , Sharan Vaswani

In the optimization of dynamical systems, the variables typically have constraints. Such problems can be modeled as a constrained Markov Decision Process (CMDP). This paper considers a model-free approach to the problem, where the…

Machine Learning · Computer Science 2021-02-02 Qinbo Bai , Vaneet Aggarwal , Ather Gattami

We study reinforcement learning (RL) with linear function approximation in Markov Decision Processes (MDPs) satisfying \emph{linear Bellman completeness} -- a fundamental setting where the Bellman backup of any linear value function remains…

Machine Learning · Computer Science 2026-03-25 Zakaria Mhammedi , Alexander Rakhlin , Nneka Okolo

In this work, we present the first finite-time analysis of Q-learning with time-varying learning policies (i.e., on-policy sampling) for discounted Markov decision processes under minimal assumptions, requiring only the existence of a…

Machine Learning · Computer Science 2026-04-07 Phalguni Nanda , Zaiwei Chen