English
Related papers

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

200 papers

Learning a Markov Decision Process (MDP) from a fixed batch of trajectories is a non-trivial task whose outcome's quality depends on both the amount and the diversity of the sampled regions of the state-action space. Yet, many MDPs are…

Machine Learning · Computer Science 2022-03-08 Giorgio Angelotti , Nicolas Drougard , Caroline P. C. Chanel

This paper proposes a computationally tractable algorithm for learning infinite-horizon average-reward linear Markov decision processes (MDPs) and linear mixture MDPs under the Bellman optimality condition. While guaranteeing computational…

Machine Learning · Computer Science 2024-09-25 Woojin Chae , Dabeen Lee

We study reinforcement learning in infinite-horizon discounted Markov decision processes with continuous state spaces, where data are generated online from a single trajectory under a Markovian behavior policy. To avoid maintaining an…

Machine Learning · Computer Science 2026-03-05 Shengbo Wang

Modern reinforcement learning (RL) often faces an enormous state-action space. Existing analytical results are typically for settings with a small number of state-actions, or simple models such as linearly modeled Q-functions. To derive…

Machine Learning · Computer Science 2023-02-03 Sing-Yuan Yeh , Fu-Chieh Chang , Chang-Wei Yueh , Pei-Yuan Wu , Alberto Bernacchia , Sattar Vakili

The problem of sample complexity of online reinforcement learning is often studied in the literature without taking into account any partial knowledge about the system dynamics that could potentially accelerate the learning process. In this…

Machine Learning · Computer Science 2024-06-04 Meshal Alharbi , Mardavij Roozbehani , Munther Dahleh

We study an approximation method for partially observed Markov decision processes (POMDPs) with continuous spaces. Belief MDP reduction, which has been the standard approach to study POMDPs requires rigorous approximation methods for…

Optimization and Control · Mathematics 2025-01-20 Ali Devran Kara , Erhan Bayraktar , Serdar Yuksel

We study the exploration problem with approximate linear action-value functions in episodic reinforcement learning under the notion of low inherent Bellman error, a condition normally employed to show convergence of approximate value…

Machine Learning · Computer Science 2020-06-30 Andrea Zanette , Alessandro Lazaric , Mykel Kochenderfer , Emma Brunskill

We present a model-free reinforcement learning algorithm to find an optimal policy for a finite-horizon Markov decision process while guaranteeing a desired lower bound on the probability of satisfying a signal temporal logic (STL)…

Systems and Control · Electrical Eng. & Systems 2021-09-29 Krishna C. Kalagarla , Rahul Jain , Pierluigi Nuzzo

In this paper, we use concepts from supervisory control theory of discrete event systems to propose a method to learn optimal control policies for a finite-state Markov Decision Process (MDP) in which (only) certain sequences of actions are…

Machine Learning · Computer Science 2022-01-04 Arun Raman , Keerthan Shagrithaya , Shalabh Bhatnagar

In a discounted reward Markov Decision Process (MDP), the objective is to find the optimal value function, i.e., the value function corresponding to an optimal policy. This problem reduces to solving a functional equation known as the…

Machine Learning · Computer Science 2019-06-17 Chandramouli Kamanchi , Raghuram Bharadwaj Diddigi , Shalabh Bhatnagar

Reinforcement learning in non-stationary environments is challenging due to abrupt and unpredictable changes in dynamics, often causing traditional algorithms to fail to converge. However, in many real-world cases, non-stationarity has some…

Machine Learning · Computer Science 2025-03-25 Mohsen Amiri , Sindri Magnússon

Discrete time stochastic optimal control problems and Markov decision processes (MDPs) are fundamental models for sequential decision-making under uncertainty and as such provide the mathematical framework underlying reinforcement learning…

Optimization and Control · Mathematics 2025-07-01 Arnulf Jentzen , Konrad Kleinberg , Thomas Kruse

We consider the off-policy evaluation problem of reinforcement learning using deep convolutional neural networks. We analyze the deep fitted Q-evaluation method for estimating the expected cumulative reward of a target policy, when the data…

Machine Learning · Computer Science 2022-10-05 Xiang Ji , Minshuo Chen , Mengdi Wang , Tuo Zhao

The constrained Markov decision process (CMDP) framework emerges as an important reinforcement learning approach for imposing safety or other critical objectives while maximizing cumulative reward. However, the current understanding of how…

Machine Learning · Computer Science 2024-12-11 Tian Tian , Lin F. Yang , Csaba Szepesvári

We study model-based learning of finite-window policies in tabular partially observable Markov decision processes (POMDPs). A common approach to learning under partial observability is to approximate unbounded history dependencies using…

Machine Learning · Computer Science 2026-04-02 Philip Jordan , Maryam Kamgarpour

We propose a new simple and natural algorithm for learning the optimal Q-value function of a discounted-cost Markov Decision Process (MDP) when the transition kernels are unknown. Unlike the classical learning algorithms for MDPs, such as…

Optimization and Control · Mathematics 2019-01-31 Dileep Kalathil , Vivek S. Borkar , Rahul Jain

The continuous nature of belief states in POMDPs presents significant computational challenges in learning the optimal policy. In this paper, we consider an approach that solves a Partially Observable Reinforcement Learning (PORL) problem…

Machine Learning · Computer Science 2025-10-15 Ameya Anjarlekar , Rasoul Etesami , R Srikant

We consider episodic reinforcement learning in reward-mixing Markov decision processes (RMMDPs): at the beginning of every episode nature randomly picks a latent reward model among $M$ candidates and an agent interacts with the MDP…

Machine Learning · Computer Science 2022-10-07 Jeongyeol Kwon , Yonathan Efroni , Constantine Caramanis , Shie Mannor

Q-functions are widely used in discrete-time learning and control to model future costs arising from a given control policy, when the initial state and input are given. Although some of their properties are understood, Q-functions…

Optimization and Control · Mathematics 2019-02-21 Joseph Warrington

We consider synthesis of control policies that maximize the probability of satisfying given temporal logic specifications in unknown, stochastic environments. We model the interaction between the system and its environment as a Markov…

Systems and Control · Computer Science 2014-05-01 Jie Fu , Ufuk Topcu