中文
相关论文

相关论文: Optimal Data Acquisition for Reinforcement Learnin…

200 篇论文

We study the problem of reinforcement learning in infinite-horizon discounted linear Markov decision processes (MDPs), and propose the first computationally efficient algorithm achieving rate-optimal regret guarantees in this setting. Our…

机器学习 · 计算机科学 2026-03-16 Antoine Moulin , Gergely Neu , Luca Viano

Reinforcement Learning is a powerful framework for training agents to navigate different situations, but it is susceptible to changes in environmental dynamics. However, solving Markov Decision Processes that are robust to changes is…

机器学习 · 计算机科学 2024-06-21 Etash Kumar Guha

We consider the problem of learning the optimal policy for Markov decision processes with safety constraints. We formulate the problem in a reach-avoid setup. Our goal is to design online reinforcement learning algorithms that ensure safety…

机器学习 · 计算机科学 2026-01-21 Abhijit Mazumdar , Rafal Wisniewski , Manuela L. Bujorianu

This paper presents a model-free reinforcement learning (RL) algorithm to solve the risk-averse optimal control (RAOC) problem for discrete-time nonlinear systems. While successful RL algorithms have been presented to learn optimal control…

系统与控制 · 电气工程与系统科学 2021-03-29 Yuzhen Han , Majid Mazouchi , Subramanya Nageshrao , Hamidreza Modares

We present an iterative inverse reinforcement learning algorithm to infer optimal cost functions in continuous spaces. Based on a popular maximum entropy criteria, our approach iteratively finds a weight improvement step and proposes a…

机器学习 · 计算机科学 2025-05-14 Sarmad Mehrdad , Avadesh Meduri , Ludovic Righetti

A default assumption in the design of reinforcement-learning algorithms is that a decision-making agent always explores to learn optimal behavior. In sufficiently complex environments that approach the vastness and scale of the real world,…

机器学习 · 计算机科学 2024-07-23 Dilip Arumugam , Saurabh Kumar , Ramki Gummadi , Benjamin Van Roy

Reinforcement learning (RL) is an important field of research in machine learning that is increasingly being applied to complex optimization problems in physics. In parallel, concepts from physics have contributed to important advances in…

机器学习 · 计算机科学 2023-05-11 Argenis Arriojas , Jacob Adamczyk , Stas Tiomkin , Rahul V. Kulkarni

Policy evaluation estimates the performance of a policy by (1) collecting data from the environment and (2) processing raw data into a meaningful estimate. Due to the sequential nature of reinforcement learning, any improper data-collecting…

机器学习 · 计算机科学 2025-03-21 Shuze Daniel Liu , Claire Chen , Shangtong Zhang

We propose a formulation of the stochastic cutting stock problem as a discounted infinite-horizon Markov decision process. At each decision epoch, given current inventory of items, an agent chooses in which patterns to cut objects in stock…

最优化与控制 · 数学 2022-06-29 Anselmo R. Pitombeira-Neto , Arthur H. Fonseca Murta

Experience replay is a core ingredient of modern deep reinforcement learning, yet its benefits in policy optimization are poorly understood beyond empirical heuristics. This paper develops a novel theoretical framework for experience replay…

机器学习 · 计算机科学 2026-02-04 Hua Zheng , Wei Xie , M. Ben Feng

Although in recent years reinforcement learning has become very popular the number of successful applications to different kinds of operations research problems is rather scarce. Reinforcement learning is based on the well-studied dynamic…

机器学习 · 计算机科学 2020-04-03 Manuel Schneckenreither

Policy gradient methods are among the most effective methods in challenging reinforcement learning problems with large state and/or action spaces. However, little is known about even their most basic theoretical convergence properties,…

机器学习 · 计算机科学 2020-10-16 Alekh Agarwal , Sham M. Kakade , Jason D. Lee , Gaurav Mahajan

We study offline reinforcement learning problems with a long-run average reward objective. The state-action pairs generated by any fixed behavioral policy thus follow a Markov chain, and the {\em empirical} state-action-next-state…

最优化与控制 · 数学 2025-03-18 Mengmeng Li , Daniel Kuhn , Tobias Sutter

We propose a general framework for sequential and dynamic acquisition of useful information in order to solve a particular task. While our goal could in principle be tackled by general reinforcement learning, our particular setting is…

机器学习 · 统计学 2016-02-09 He He , Paul Mineiro , Nikos Karampatziakis

We consider the batch (off-line) policy learning problem in the infinite horizon Markov Decision Process. Motivated by mobile health applications, we focus on learning a policy that maximizes the long-term average reward. We propose a…

统计理论 · 数学 2022-09-20 Peng Liao , Zhengling Qi , Runzhe Wan , Predrag Klasnja , Susan Murphy

Reinforcement learning considers the problem of finding policies that maximize an expected cumulative reward in a Markov decision process with unknown transition probabilities. In this paper we consider the problem of finding optimal…

机器学习 · 计算机科学 2020-10-19 Santiago Paternain , Juan Andres Bazerque , Alejandro Ribeiro

One of the main challenges in real-world reinforcement learning is to learn successfully from limited training samples. We show that in certain settings, the available data can be dramatically increased through a form of multi-task…

机器学习 · 计算机科学 2021-02-19 Desmond Cai , Shiau Hong Lim , Laura Wynter

In order for reinforcement learning techniques to be useful in real-world decision making processes, they must be able to produce robust performance from limited data. Deep policy optimization methods have achieved impressive results on…

机器学习 · 计算机科学 2020-12-22 James Queeney , Ioannis Ch. Paschalidis , Christos G. Cassandras

Relevant and high-quality data are critical to successful development of machine learning applications. For machine learning applications on dynamic systems equipped with a large number of sensors, such as connected vehicles and robots, how…

机器学习 · 计算机科学 2021-08-31 Alp Sahin , Xiangrui Zeng

We propose a new randomized optimization method for high-dimensional problems which can be seen as a generalization of coordinate descent to random subspaces. We show that an adaptive sampling strategy for the random subspace significantly…

最优化与控制 · 数学 2019-12-19 Jonathan Lacotte , Mert Pilanci , Marco Pavone