English
Related papers

Related papers: Finite Sample Analysis of Two-Timescale Stochastic…

200 papers

In this paper, we consider the problem of learning safe policies for probabilistic-constrained reinforcement learning (RL). Specifically, a safe policy or controller is one that, with high probability, maintains the trajectory of the agent…

Machine Learning · Computer Science 2024-03-14 Weiqin Chen , Dharmashankar Subramanian , Santiago Paternain

Value-function approximation methods that operate in batch mode have foundational importance to reinforcement learning (RL). Finite sample guarantees for these methods often crucially rely on two types of assumptions: (1) mild distribution…

Machine Learning · Computer Science 2019-05-02 Jinglin Chen , Nan Jiang

Meta reinforcement learning (RL) allows agents to leverage experience across a distribution of tasks on which the agent can train at will, enabling faster learning of optimal policies on new test tasks. Despite its success in improving…

Machine Learning · Computer Science 2026-05-27 Tingting Ni , Maryam Kamgarpour

Temporal difference (TD) learning is a foundational algorithm in reinforcement learning (RL). For nearly forty years, TD learning has served as a workhorse for applied RL as well as a building block for more complex and specialized…

Machine Learning · Computer Science 2025-06-24 Hwanwoo Kim , Panos Toulis , Eric Laber

We consider convex-concave saddle-point problems where the objective functions may be split in many components, and extend recent stochastic variance reduction methods (such as SVRG or SAGA) to provide the first large-scale linearly…

Machine Learning · Computer Science 2016-11-04 P Balamurugan , Francis Bach

Sample average approximation (SAA), a popular method for tractably solving stochastic optimization problems, enjoys strong asymptotic performance guarantees in settings with independent training samples. However, these guarantees are not…

Optimization and Control · Mathematics 2021-12-13 Yafei Wang , Bo Pan , Wei Tu , Peng Liu , Bei Jiang , Chao Gao , Wei Lu , Shangling Jui , Linglong Kong

Inference time latency has remained an open challenge for real world applications of large language models (LLMs). State-of-the-art (SOTA) speculative sampling (SpS) methods for LLMs, like EAGLE-3, use tree-based drafting to explore…

Machine Learning · Computer Science 2026-01-21 Chenan Wang , Daniel H. Shi , Haipeng Chen

The first aim of this paper is to establish the weak convergence rate of nonlinear two-time-scale stochastic approximation algorithms. Its second aim is to introduce the averaging principle in the context of two-time-scale stochastic…

Probability · Mathematics 2007-05-23 Abdelkader Mokkadem , Mariane Pelletier

One of the fundamental challenges associated with reinforcement learning (RL) is that collecting sufficient data can be both time-consuming and expensive. In this paper, we formalize a concept of time reversal symmetry in a Markov decision…

Machine Learning · Computer Science 2023-11-29 Brett Barkley , Amy Zhang , David Fridovich-Keil

Viewing a two time scale stochastic approximation scheme as a noisy discretization of a singularly perturbed differential equation, we obtain a concentration bound for its iterates that captures its behavior with quantifiable high…

Optimization and Control · Mathematics 2018-06-29 Vivek S. Borkar , Sarath Pattathil

In this paper we explore methods to exploit symmetries for ensuring sample efficiency in reinforcement learning (RL), this problem deserves ever increasing attention with the recent advances in the use of deep networks for complex RL tasks…

Machine Learning · Statistics 2017-06-12 Anuj Mahajan , Theja Tulabandhula

Function approximation has been an indispensable component in modern reinforcement learning algorithms designed to tackle problems with large state spaces in high dimensions. This paper reviews recent results on error analysis for these…

Machine Learning · Computer Science 2024-02-27 Jihao Long , Jiequn Han

Most provably-efficient learning algorithms introduce optimism about poorly-understood states and actions to encourage exploration. We study an alternative approach for efficient exploration, posterior sampling for reinforcement learning…

Machine Learning · Statistics 2013-12-30 Ian Osband , Daniel Russo , Benjamin Van Roy

In finance, sequential decision problems are often faced, for which reinforcement learning (RL) emerges as a promising tool for optimisation without the need of analytical tractability. However, the objective of classical RL is the expected…

Computational Finance · Quantitative Finance 2026-02-13 Federico Cacciamani , Roberto Daluiso , Marco Pinciroli , Michele Trapletti , Edoardo Vittori

In this paper, we introduce a new stochastic approximation (SA) type algorithm, namely the randomized stochastic gradient (RSG) method, for solving an important class of nonlinear (possibly nonconvex) stochastic programming (SP) problems.…

Optimization and Control · Mathematics 2015-10-27 Saeed Ghadimi , Guanghui Lan

We study constrained reinforcement learning (CRL) from a novel perspective by setting constraints directly on state density functions, rather than the value functions considered by previous works. State density has a clear physical and…

Machine Learning · Computer Science 2021-06-25 Zengyi Qin , Yuxiao Chen , Chuchu Fan

Achieving sample efficiency in online episodic reinforcement learning (RL) requires optimally balancing exploration and exploitation. When it comes to a finite-horizon episodic Markov decision process with $S$ states, $A$ actions and…

Machine Learning · Computer Science 2022-10-18 Gen Li , Laixi Shi , Yuxin Chen , Yuejie Chi

Temporal difference learning (TD) is a simple iterative algorithm used to estimate the value function corresponding to a given policy in a Markov decision process. Although TD is one of the most widely used algorithms in reinforcement…

Machine Learning · Computer Science 2018-11-07 Jalaj Bhandari , Daniel Russo , Raghav Singal

Reinforcement Learning (RL) controllers have generated excitement within the control community. The primary advantage of RL controllers relative to existing methods is their ability to optimize uncertain systems independently of explicit…

Machine Learning · Computer Science 2021-12-07 Max Mowbray , Panagiotis Petsagkourakis , Ehecatl Antonio del Río Chanona , Dongda Zhang

This work, for the first time, introduces two constant factor approximation algorithms with linear query complexity for non-monotone submodular maximization over a ground set of size $n$ subject to a knapsack constraint, $\mathsf{DLA}$ and…

Data Structures and Algorithms · Computer Science 2023-07-11 Canh V. Pham , Tan D. Tran , Dung T. K. Ha , My T. Thai