English
Related papers

Related papers: Multi-Bellman operator for convergence of $Q$-lear…

200 papers

Q-learning with neural network function approximation (neural Q-learning for short) is among the most prevalent deep reinforcement learning algorithms. Despite its empirical success, the non-asymptotic convergence rate of neural Q-learning…

Machine Learning · Computer Science 2020-03-05 Pan Xu , Quanquan Gu

When function approximation is used, solving the Bellman optimality equation with stability guarantees has remained a major open problem in reinforcement learning for decades. The fundamental difficulty is that the Bellman operator may…

Machine Learning · Computer Science 2018-06-07 Bo Dai , Albert Shaw , Lihong Li , Lin Xiao , Niao He , Zhen Liu , Jianshu Chen , Le Song

Fitted $Q$-iteration (FQI) and soft FQI are widely used value-based methods for offline reinforcement learning, but their standard stability guarantees often depend on Bellman completeness, a strong closure condition that can fail under…

Machine Learning · Statistics 2026-05-11 Lars van der Laan , Nathan Kallus

While many problems in machine learning focus on learning mappings between finite-dimensional spaces, scientific applications require approximating mappings between function spaces, i.e., operators. We study the problem of learning…

Machine Learning · Computer Science 2025-10-30 Adrien Weihs , Jingmin Sun , Zecheng Zhang , Hayden Schaeffer

In this paper, we study the theoretical properties of the projected Bellman equation (PBE) and two algorithms to solve this equation: linear Q-learning and approximate value iteration (AVI). We consider two sufficient conditions for the…

Artificial Intelligence · Computer Science 2025-04-16 Han-Dong Lim , Donghwan Lee

The optimistic nature of the Q-learning target leads to an overestimation bias, which is an inherent problem associated with standard $Q-$learning. Such a bias fails to account for the possibility of low returns, particularly in risky…

Machine Learning · Computer Science 2021-11-05 Thommen George Karimpanal , Hung Le , Majid Abdolshah , Santu Rana , Sunil Gupta , Truyen Tran , Svetha Venkatesh

The paper introduces the first formulation of convex Q-learning for Markov decision processes with function approximation. The algorithms and theory rest on a relaxation of a dual of Manne's celebrated linear programming characterization of…

Optimization and Control · Mathematics 2023-09-12 Fan Lu , Sean Meyn

The purpose of this paper is to study the convergence of the quasi-maximum likelihood (QML) estimator for long memory linear processes. We first establish a correspondence between the long-memory linear process representation and the…

Statistics Theory · Mathematics 2024-05-24 Jean-Marc Bardet , Yves Gael Tchabo Mbienkeu

Understanding the theoretical capabilities and limitations of quantum machine learning (QML) models to solve machine learning tasks is crucial to advancing both quantum software and hardware developments. Similarly to the classical setting,…

Quantum Physics · Physics 2026-03-31 Qiuhao Chen , Yuling Jiao , Yinan Li , Xiliang Lu , Jerry Zhijian Yang

The vast majority of Reinforcement Learning methods is largely impacted by the computation effort and data requirements needed to obtain effective estimates of action-value functions, which in turn determine the quality of the overall…

Machine Learning · Computer Science 2025-04-04 Théo Vincent , Daniel Palenicek , Boris Belousov , Jan Peters , Carlo D'Eramo

Recently Koopman operator has become a promising data-driven tool to facilitate real-time control for unknown nonlinear systems. It maps nonlinear systems into equivalent linear systems in embedding space, ready for real-time linear control…

Robotics · Computer Science 2022-06-16 Haojie Shi , Max Q. -H. Meng

Reinforcement learning has driven impressive advances in machine learning. Simultaneously, quantum-enhanced machine learning algorithms using quantum annealing underlie heavy developments. Recently, a multi-agent reinforcement learning…

Artificial Intelligence · Computer Science 2021-11-23 Tobias Müller , Christoph Roch , Kyrill Schmid , Philipp Altmann

Transfer and Koopman operator methods offer a framework for representing complex, nonlinear dynamical systems via linear transformations, enabling a deeper understanding of the underlying dynamics. The spectra of these operators provide…

Dynamical Systems · Mathematics 2026-03-25 Gary Froyland , Kevin Kühl

We focus on the linear convergence of generalized proximal point algorithms for solving monotone inclusion problems. Under the assumption that the associated monotone operator is metrically subregular or that the inverse of the monotone…

Optimization and Control · Mathematics 2022-03-29 Hui Ouyang

Koopman analysis of a general dynamics system provides a linear Koopman operator and an embedded eigenfunction space, enabling the application of standard techniques from linear analysis. However, in practice, deriving exact operators and…

Systems and Control · Electrical Eng. & Systems 2025-04-29 Alexander Estornell , Leonard Jung , Alenna Spiro , Mario Sznaier , Michael Everett

This work investigates the properties of the proximity operator for quasar-convex functions and establishes the convergence of the proximal point algorithm to a global minimizer with a particular focus on its convergence rate. In…

Optimization and Control · Mathematics 2026-04-16 José de Brito , Felipe Lara , Di Liu

We propose a new reinforcement learning algorithm derived from a regularized linear-programming formulation of optimal control in MDPs. The method is closely related to the classic Relative Entropy Policy Search (REPS) algorithm of Peters…

Machine Learning · Computer Science 2021-03-01 Joan Bas-Serrano , Sebastian Curi , Andreas Krause , Gergely Neu

Recent work has shown a variety of ways in which machine learning can be used to accelerate the solution of constrained optimization problems. Increasing demand for real-time decision-making capabilities in applications such as artificial…

Machine Learning · Computer Science 2024-04-02 Ethan King , James Kotary , Ferdinando Fioretto , Jan Drgona

Koopman operator theory provides a framework for nonlinear dynamical system analysis and time-series forecasting by mapping dynamics to a space of real-valued measurement functions, enabling a linear operator representation. Despite the…

Machine Learning · Computer Science 2025-06-18 Yitian Zhang , Liheng Ma , Antonios Valkanas , Boris N. Oreshkin , Mark Coates

We devise a control-theoretic reinforcement learning approach to support direct learning of the optimal policy. We establish various theoretical properties of our approach, such as convergence and optimality of our analog of the Bellman…

Machine Learning · Computer Science 2026-04-01 Weiqin Chen , Mark S. Squillante , Chai Wah Wu , Santiago Paternain