English
Related papers

Related papers: A Statistical Analysis of Polyak-Ruppert Averaged …

200 papers

Recently regular decision processes have been proposed as a well-behaved form of non-Markov decision process. Regular decision processes are characterised by a transition function and a reward function that depend on the whole history,…

Artificial Intelligence · Computer Science 2022-05-19 Alessandro Ronca , Giuseppe De Giacomo

The Lipschitz bandit is a key variant of stochastic bandit problems where the expected reward function satisfies a Lipschitz condition with respect to an arm metric space. With its wide-ranging practical applications, various Lipschitz…

Machine Learning · Computer Science 2025-11-25 Bongsoo Yi , Yue Kang , Yao Li

In this article we establish central limit theorems for multilevel Polyak-Ruppert averaged stochastic approximation schemes. We work under very mild technical assumptions and consider the slow regime in wich typical errors decay like…

Probability · Mathematics 2019-12-18 Steffen Dereich

We study the problem of online learning and online regret minimization when samples are drawn from a general unknown non-stationary process. We introduce the concept of a dynamic changing process with cost $K$, where the conditional…

Machine Learning · Computer Science 2023-11-14 Changlong Wu , Ananth Grama , Wojciech Szpankowski

Online reinforcement learning in non-episodic, finite-horizon MDPs remains underexplored and is challenged by the need to estimate returns to a fixed terminal time. Existing infinite-horizon methods, which often rely on discounted…

Machine Learning · Computer Science 2026-02-03 Jiamin Xu , Kyra Gan

Model-free reinforcement learning (RL) algorithms, such as Q-learning, directly parameterize and update value functions or policies without explicitly modeling the environment. They are typically simpler, more flexible to use, and thus more…

Machine Learning · Computer Science 2018-07-11 Chi Jin , Zeyuan Allen-Zhu , Sebastien Bubeck , Michael I. Jordan

We propose a new Q-learning variant, called 2RA Q-learning, that addresses some weaknesses of existing Q-learning methods in a principled manner. One such weakness is an underlying estimation bias which cannot be controlled and often…

Optimization and Control · Mathematics 2024-05-30 Peter Schmitt-Förster , Tobias Sutter

We propose an epoch-based reinforcement learning algorithm for infinite-horizon average-cost Markov decision processes (MDPs) that leverages a partial order over a policy class. In this structure, $\pi' \leq \pi$ if data collected under…

Machine Learning · Statistics 2025-08-07 Zhongjun Zhang , Shipra Agrawal , Ilan Lobel , Sean R. Sinclair , Christina Lee Yu

We study reinforcement learning with linear function approximation and finite-memory approximations for partially observed Markov decision processes (POMDPs). We first present an algorithm for the value evaluation of finite-memory feedback…

Optimization and Control · Mathematics 2025-05-22 Ali Devran Kara

We propose a new risk-constrained formulation of the classical Linear Quadratic (LQ) stochastic control problem for general partially-observed systems. Our framework is motivated by the fact that the risk-neutral LQ controllers, although…

Optimization and Control · Mathematics 2021-12-15 Anastasios Tsiamis , Dionysios S. Kalogerias , Alejandro Ribeiro , George J. Pappas

This paper studies an infinite horizon optimal control problem for discrete-time linear systems and quadratic criteria, both with random parameters which are independent and identically distributed with respect to time. A classical approach…

Optimization and Control · Mathematics 2020-11-11 Kai Du , Qingxin Meng , Fu Zhang

In the past few years, off-policy reinforcement learning methods have shown promising results in their application for robot control. Deep Q-learning, however, still suffers from poor data-efficiency and is susceptible to stochasticity in…

Machine Learning · Computer Science 2020-08-17 Gabriel Kalweit , Maria Huegle , Joschka Boedecker

The dominant framework for off-policy multi-goal reinforcement learning involves estimating goal conditioned Q-value function. When learning to achieve multiple goals, data efficiency is intimately connected with the generalization of the…

Artificial Intelligence · Computer Science 2023-06-28 Zhang-Wei Hong , Ge Yang , Pulkit Agrawal

Although there is an extensive body of work characterizing the sample complexity of discounted-return offline RL with function approximations, prior work on the average-reward setting has received significantly less attention, and existing…

Machine Learning · Computer Science 2025-10-21 Jongmin Lee , Ernest K. Ryu

Reinforcement learning (RL) is a control approach that can handle nonlinear stochastic optimal control problems. However, despite the promise exhibited, RL has yet to see marked translation to industrial practice primarily due to its…

Machine Learning · Computer Science 2021-04-15 Elton Pan , Panagiotis Petsagkourakis , Max Mowbray , Dongda Zhang , Antonio del Rio-Chanona

Q-learning suffers from overestimation bias, because it approximates the maximum action value using the maximum estimated action value. Algorithms have been proposed to reduce overestimation bias, but we lack an understanding of how bias…

Machine Learning · Computer Science 2021-08-10 Qingfeng Lan , Yangchen Pan , Alona Fyshe , Martha White

We study reinforcement learning (RL) for learning a Quantal Stackelberg Equilibrium (QSE) in an episodic Markov game with a leader-follower structure. In specific, at the outset of the game, the leader announces her policy to the follower…

Machine Learning · Computer Science 2023-07-27 Siyu Chen , Mengdi Wang , Zhuoran Yang

The balance between exploration and exploitation is a key problem for reinforcement learning methods, especially for Q-learning. In this paper, a fidelity-based probabilistic Q-learning (FPQL) approach is presented to naturally solve this…

Machine Learning · Computer Science 2018-06-11 Chunlin Chen , Daoyi Dong , Han-Xiong Li , Jian Chu , Tzyh-Jong Tarn

The paper concerns the $d$-dimensional stochastic approximation recursion, $$ \theta_{n+1}= \theta_n + \alpha_{n + 1} f(\theta_n, \Phi_{n+1}) $$ where $ \{ \Phi_n \}$ is a stochastic process on a general state space, satisfying a…

Statistics Theory · Mathematics 2024-11-18 Vivek Borkar , Shuhang Chen , Adithya Devraj , Ioannis Kontoyiannis , Sean Meyn

Q-learning is a promising method for solving optimal control problems for uncertain systems without the explicit need for system identification. However, approaches for continuous-time Q-learning have limited provable safety guarantees,…

Systems and Control · Electrical Eng. & Systems 2024-01-30 Soutrik Bandyopadhyay , Shubhendu Bhasin