English
Related papers

Related papers: Stochastic Approximation with Unbounded Markovian …

200 papers

This work analyzes the stochastic approximation algorithm with non-decaying gains as applied in time-varying problems. The setting is to minimize a sequence of scalar-valued loss functions $f_k(\cdot)$ at sampling times $\tau_k$ or to…

Optimization and Control · Mathematics 2020-03-18 Jingyi Zhu

This paper is concerned with the sample efficiency of reinforcement learning, assuming access to a generative model (or simulator). We first consider $\gamma$-discounted infinite-horizon Markov decision processes (MDPs) with state space…

Machine Learning · Computer Science 2025-03-18 Gen Li , Yuting Wei , Yuejie Chi , Yuxin Chen

As machine learning applications grow increasingly ubiquitous and complex, they face an increasing set of requirements beyond accuracy. The prevalent approach to handle this challenge is to aggregate a weighted combination of requirement…

Machine Learning · Computer Science 2026-01-07 Aneesh Barthakur , Luiz F. O. Chamon

Motivated by practical applications where stable long-term performance is critical-such as robotics, operations research, and healthcare-we study the problem of distributionally robust (DR) average-reward reinforcement learning. We propose…

Machine Learning · Computer Science 2026-02-03 Zijun Chen , Shengbo Wang , Nian Si

We propose new continuous-time formulations for first-order stochastic optimization algorithms such as mini-batch gradient descent and variance-reduced methods. We exploit these continuous-time models, together with simple Lyapunov analysis…

Optimization and Control · Mathematics 2020-03-12 Antonio Orvieto , Aurelien Lucchi

We address stability of a class of Markovian discrete-time stochastic hybrid systems. This class of systems is characterized by the state-space of the system being partitioned into a safe or target set and its exterior, and the dynamics of…

Optimization and Control · Mathematics 2011-03-09 Debasish Chatterjee , Soumik Pal

Reinforcement Learning (RL) serves as a versatile framework for sequential decision-making, finding applications across diverse domains such as robotics, autonomous driving, recommendation systems, supply chain optimization, biology,…

Machine Learning · Computer Science 2024-08-26 Vaneet Aggarwal , Washim Uddin Mondal , Qinbo Bai

Trajectory optimization under uncertainty underpins a wide range of applications in robotics. However, existing methods are limited in terms of reasoning about sources of epistemic and aleatoric uncertainty, space and time correlations,…

Robotics · Computer Science 2023-09-28 Thomas Lew , Riccardo Bonalli , Marco Pavone

Sample average approximation (SAA) replaces an intractable expected objective by an empirical average and is a basic device of modern stochastic optimization. We develop a rate theory for optimal values and empirical…

Optimization and Control · Mathematics 2026-04-29 Hien Duy Nguyen , Jacob Westerhout , Xin Guo

We introduce a class of learning problems where the agent is presented with a series of tasks. Intuitively, if there is relation among those tasks, then the information gained during execution of one task has value for the execution of…

Machine Learning · Computer Science 2012-09-06 Christos Dimitrakakis

Establishing almost sure convergence rates for stochastic approximation and reinforcement learning under Markovian noise is a fundamental theoretical challenge. We make progress towards this challenge for a class of stochastic approximation…

Machine Learning · Computer Science 2026-05-11 Xinyu Liu , Zixuan Xie , Shangtong Zhang

We study personalized multi-agent average reward TD learning, in which a collection of agents interacts with different environments and jointly learns their respective value functions. We focus on the setting where there exists a shared…

Machine Learning · Computer Science 2026-03-10 Leo Muxing Wang , Pengkun Yang , Lili Su

Many machine learning and optimization algorithms are built upon the framework of stochastic approximation (SA), for which the selection of step-size (or learning rate) $\{\alpha_n\}$ is crucial for success. An essential condition for…

Statistics Theory · Mathematics 2025-08-05 Caio Kalil Lauand , Sean Meyn

Generalization error (also known as the out-of-sample error) measures how well the hypothesis learned from training data generalizes to previously unseen data. Proving tight generalization error bounds is a central question in statistical…

Machine Learning · Computer Science 2020-03-03 Jian Li , Xuanyuan Luo , Mingda Qiao

In recent years deep neural networks have been successfully applied to the domains of reinforcement learning \cite{bengio2009learning,krizhevsky2012imagenet,hinton2006reducing}. Deep reinforcement learning \cite{mnih2015human} is reported…

Machine Learning · Computer Science 2020-05-19 Huihui Zhang , Wu Huang

In this paper, we study the stochastic probing problem under a general monotone norm objective. Given a ground set $U = [n]$, each element $i \in U$ has an independent nonnegative random variable $X_i$ with known distribution. Probing an…

Data Structures and Algorithms · Computer Science 2025-10-17 Jian Li , Yinchen Liu , Yiran Zhang

We derive uniform all-time concentration bound of the type 'for all $n \geq n_0$ for some $n_0$' for TD(0) with linear function approximation. We work with online TD learning with samples from a single sample path of the underlying Markov…

Machine Learning · Computer Science 2026-01-13 Siddharth Chandak , Vivek S. Borkar

An important question in deep learning is how higher-order optimization methods affect generalization. In this work, we analyze a stochastic Gauss-Newton (SGN) method with Levenberg-Marquardt damping and mini-batch sampling for training…

Machine Learning · Computer Science 2025-11-13 Semih Cayci

We study the policy evaluation problem in multi-agent reinforcement learning where a group of agents, with jointly observed states and private local actions and rewards, collaborate to learn the value function of a given policy via local…

Optimization and Control · Mathematics 2021-11-08 Dongsheng Ding , Xiaohan Wei , Zhuoran Yang , Zhaoran Wang , Mihailo R. Jovanović

Recent non-asymptotic analyses have substantially advanced the theory of distributional policy evaluation, but they largely concern synchronous full-state updates under a generative model, model-based estimators, accelerated variants, or…

Machine Learning · Computer Science 2026-05-11 Ege C. Kaya , Abolfazl Hashemi