English
Related papers

Related papers: Linear $Q$-Learning Does Not Diverge in $L^2$: Con…

200 papers

We analyze the convergence rate of the unregularized natural policy gradient algorithm with log-linear policy parametrizations in infinite-horizon discounted Markov decision processes. In the deterministic case, when the Q-value is known…

Machine Learning · Computer Science 2023-03-15 Carlo Alfano , Patrick Rebeschini

Q-learning, which seeks to learn the optimal Q-function of a Markov decision process (MDP) in a model-free fashion, lies at the heart of reinforcement learning. When it comes to the synchronous setting (such that independent samples for all…

Machine Learning · Statistics 2025-03-18 Gen Li , Changxiao Cai , Yuxin Chen , Yuting Wei , Yuejie Chi

We present a distributional approach to theoretical analyses of reinforcement learning algorithms for constant step-sizes. We demonstrate its effectiveness by presenting simple and unified proofs of convergence for a variety of…

Machine Learning · Computer Science 2020-03-30 Philip Amortila , Doina Precup , Prakash Panangaden , Marc G. Bellemare

The main objective of this research paper is to investigate the local convergence characteristics of Model-agnostic Meta-learning (MAML) when applied to linear system quadratic optimal control (LQR). MAML and its variations have become…

Systems and Control · Electrical Eng. & Systems 2023-09-18 Negin Musavi , Geir E. Dullerud

We analyze speed of convergence to global optimum for gradient descent training a deep linear neural network (parameterized as $x \mapsto W_N W_{N-1} \cdots W_1 x$) by minimizing the $\ell_2$ loss over whitened data. Convergence at a linear…

Machine Learning · Computer Science 2019-10-29 Sanjeev Arora , Nadav Cohen , Noah Golowich , Wei Hu

Ensuring safety during reinforcement learning (RL) training is critical in real-world applications where unsafe exploration can lead to devastating outcomes. While most safe RL methods mitigate risk through constraints or penalization, they…

Machine Learning · Computer Science 2026-04-29 Yeeun Lim , Narim Jeong , Donghwan Lee

In this paper, we consider reinforcement learning of nonlinear systems with continuous state and action spaces. We present an episodic learning algorithm, where we for each episode use convex optimization to find a two-layer neural network…

Optimization and Control · Mathematics 2024-06-25 Ather Gattami

This paper develops a sign-separated finite-time error analysis for constant step-size Q-learning. Starting from the switching-system representation, the error is decomposed into its componentwise negative and positive parts. The negative…

Artificial Intelligence · Computer Science 2026-05-18 Donghwan Lee

Offline reinforcement learning is important in domains such as medicine, economics, and e-commerce where online experimentation is costly, dangerous or unethical, and where the true model is unknown. However, most methods assume all…

Machine Learning · Statistics 2025-10-30 David Bruns-Smith , Angela Zhou

In this work, we present a new model-free and off-policy reinforcement learning (RL) algorithm, that is capable of finding a near-optimal policy with state-action observations from arbitrary behavior policies. Our algorithm, called the…

Optimization and Control · Mathematics 2025-07-21 Narim Jeong , Donghwan Lee , Niao He

We seek to learn an effective policy for a Markov Decision Process (MDP) with continuous states via Q-Learning. Given a set of basis functions over state action pairs we search for a corresponding set of linear weights that minimizes the…

Machine Learning · Computer Science 2013-09-27 Charles Tripp , Ross D. Shachter

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

We study approximation and learning capacities of convolutional neural networks (CNNs) with one-side zero-padding and multiple channels. Our first result proves a new approximation bound for CNNs with certain constraint on the weights. Our…

Machine Learning · Computer Science 2025-07-29 Yunfei Yang , Han Feng , Ding-Xuan Zhou

Fitted $Q$-evaluation (FQE) is a standard regression-based tool for off-policy evaluation, but existing stability guarantees often rely on Bellman completeness, a strong closure condition that can fail under function approximation. We study…

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

We study the problem of learning-to-learn: inferring a learning algorithm that works well on tasks sampled from an unknown distribution. As class of algorithms we consider Stochastic Gradient Descent on the true risk regularized by the…

Machine Learning · Computer Science 2019-03-26 Giulia Denevi , Carlo Ciliberto , Riccardo Grazzi , Massimiliano Pontil

Fully decentralized learning, where the global information, i.e., the actions of other agents, is inaccessible, is a fundamental challenge in cooperative multi-agent reinforcement learning. However, the convergence and optimality of most…

Machine Learning · Computer Science 2023-02-03 Jiechuan Jiang , Zongqing Lu

Quantum neural networks (QNNs) are a framework for creating quantum algorithms that promises to combine the speedups of quantum computation with the widespread successes of machine learning. A major challenge in QNN development is a…

Quantum Physics · Physics 2021-06-18 Maria Kieferova , Ortiz Marrero Carlos , Nathan Wiebe

Recent methods for imitation learning directly learn a $Q$-function using an implicit reward formulation rather than an explicit reward function. However, these methods generally require implicit reward regularization to improve stability…

Machine Learning · Computer Science 2023-03-02 Firas Al-Hafez , Davide Tateo , Oleg Arenz , Guoping Zhao , Jan Peters

Offline reinforcement learning leverages large datasets to train policies without interactions with the environment. The learned policies may then be deployed in real-world settings where interactions are costly or dangerous. Current…

Machine Learning · Computer Science 2022-06-29 Matthias Weissenbacher , Samarth Sinha , Animesh Garg , Yoshinobu Kawahara

In this paper, we derive a generalization of the Speedy Q-learning (SQL) algorithm that was proposed in the Reinforcement Learning (RL) literature to handle slow convergence of Watkins' Q-learning. In most RL algorithms such as Q-learning,…

Machine Learning · Computer Science 2020-02-14 Indu John , Chandramouli Kamanchi , Shalabh Bhatnagar