中文
相关论文

相关论文: Toward Optimal Statistical Inference in Noisy Line…

200 篇论文

The recent emergence of reinforcement learning has created a demand for robust statistical inference methods for the parameter estimates computed using these algorithms. Existing methods for statistical inference in online learning are…

机器学习 · 统计学 2022-06-29 Pratik Ramprasad , Yuantong Li , Zhuoran Yang , Zhaoran Wang , Will Wei Sun , Guang Cheng

We explore reinforcement learning methods for finding the optimal policy in the linear quadratic regulator (LQR) problem. In particular, we consider the convergence of policy gradient methods in the setting of known and unknown parameters.…

机器学习 · 计算机科学 2021-06-25 Ben Hambly , Renyuan Xu , Huining Yang

Policy gradient (PG) methods are the backbone of many reinforcement learning algorithms due to their good performance in policy optimization problems. As a gradient-based approach, PG methods typically rely on knowledge of the system…

系统与控制 · 电气工程与系统科学 2026-04-02 Bowen Song , Andrea Iannelli

We consider reinforcement learning (RL) methods for finding optimal policies in linear quadratic (LQ) mean field control (MFC) problems over an infinite horizon in continuous time, with common noise and entropy regularization. We study…

最优化与控制 · 数学 2024-08-06 Noufel Frikha , Huyên Pham , Xuanye Song

Reinforcement Learning (RL) has emerged as a powerful framework for sequential decision-making in dynamic environments, particularly when system parameters are unknown. This paper investigates RL-based control for entropy-regularized…

系统与控制 · 电气工程与系统科学 2025-12-02 Gabriel Diaz , Lucky Li , Wenhao Zhang

This paper studies the robustness of reinforcement learning algorithms to errors in the learning process. Specifically, we revisit the benchmark problem of discrete-time linear quadratic regulation (LQR) and study the long-standing open…

最优化与控制 · 数学 2021-03-16 Bo Pang , Zhong-Ping Jiang

With the outstanding performance of policy gradient (PG) method in the reinforcement learning field, the convergence theory of it has aroused more and more interest recently. Meanwhile, the significant importance and abundant theoretical…

最优化与控制 · 数学 2024-04-19 Xinpei Zhang , Guangyan Jia

This work uses the entropy-regularised relaxed stochastic control perspective as a principled framework for designing reinforcement learning (RL) algorithms. Herein agent interacts with the environment by generating noisy controls…

机器学习 · 计算机科学 2023-09-18 Lukasz Szpruch , Tanut Treetanthiploet , Yufei Zhang

We consider reinforcement learning (RL) methods in offline domains without additional online data collection, such as mobile health applications. Most of existing policy optimization algorithms in the computer science literature are…

机器学习 · 统计学 2022-07-28 Chengchun Shi , Shikai Luo , Yuan Le , Hongtu Zhu , Rui Song

We consider the finite-horizon offline reinforcement learning (RL) setting, and are motivated by the challenge of learning the policy at any step h in dynamic programming (DP) algorithms. To learn this, it is sufficient to evaluate the…

Stability is one of the most fundamental requirements for systems synthesis. In this paper, we address the stabilization problem for unknown linear systems via policy gradient (PG) methods. We leverage a key feature of PG for Linear…

最优化与控制 · 数学 2021-12-20 Feiran Zhao , Xingyun Fu , Keyou You

Policy gradient algorithms are widely used in reinforcement learning and belong to the class of approximate dynamic programming methods. This paper studies two key policy gradient algorithms, the Natural Policy Gradient and the Gauss-Newton…

系统与控制 · 电气工程与系统科学 2026-05-11 Bowen Song , Sebastien Gros , Andrea Iannelli

In reinforcement learning, it is typical to use the empirically observed transitions and rewards to estimate the value of a policy via either model-based or Q-fitting approaches. Although straightforward, these techniques in general yield…

机器学习 · 计算机科学 2020-07-28 Ilya Kostrikov , Ofir Nachum

We study computationally and statistically efficient reinforcement learning under the linear $Q^{\pi}$ realizability assumption, where any policy's $Q$-function is linear in a given state-action feature representation. Prior methods in this…

机器学习 · 计算机科学 2026-03-03 Yijing Ke , Zihan Zhang , Ruosong Wang

Offline Reinforcement Learning (RL) aims to learn policies from previously collected datasets without exploring the environment. Directly applying off-policy algorithms to offline RL usually fails due to the extrapolation error caused by…

机器学习 · 计算机科学 2022-02-24 Chenjia Bai , Lingxiao Wang , Zhuoran Yang , Zhihong Deng , Animesh Garg , Peng Liu , Zhaoran Wang

Offline reinforcement learning (RL) enables policy learning from static data but often suffers from poor coverage of the state-action space and distributional shift problems. This problem can be addressed by allowing limited online…

机器学习 · 计算机科学 2026-02-03 Soumyadeep Roy , Shashwat Kushwaha , Ambedkar Dukkipati

The linear quadratic regulator (LQR) problem has reemerged as an important theoretical benchmark for reinforcement learning-based control of complex dynamical systems with continuous state and action spaces. In contrast with nearly all…

机器学习 · 计算机科学 2020-05-04 Benjamin Gravell , Peyman Mohajerin Esfahani , Tyler Summers

This paper studies how a stochastic gradient algorithm (SG) can be controlled to hide the estimate of the local stationary point from an eavesdropper. Such problems are of significant interest in distributed optimization settings like…

机器学习 · 计算机科学 2024-05-14 Adit Jain , Vikram Krishnamurthy

This paper proposes a novel robust reinforcement learning framework for discrete-time linear systems with model mismatch that may arise from the sim-to-real gap. A key strategy is to invoke advanced techniques from control theory. Using the…

系统与控制 · 电气工程与系统科学 2023-12-07 Leilei Cui , Tamer Başar , Zhong-Ping Jiang

This paper introduces and analyzes an improved Q-learning algorithm for discrete-time linear time-invariant systems. The proposed method does not require any knowledge of the system dynamics, and it enjoys significant efficiency advantages…

系统与控制 · 电气工程与系统科学 2023-04-03 Victor G. Lopez , Mohammad Alsalti , Matthias A. Müller
‹ 上一页 1 2 3 10 下一页 ›