English
Related papers

Related papers: Convergence of Flow-Policy Gradient Learning for L…

200 papers

We introduce a one-step generative policy for offline reinforcement learning that maps noise directly to actions via a residual reformulation of MeanFlow, making it compatible with Q-learning. While one-step Gaussian policies enable fast…

Machine Learning · Computer Science 2025-11-18 Zeyuan Wang , Da Li , Yulin Chen , Ye Shi , Liang Bai , Tianyuan Yu , Yanwei Fu

There is growing interest in utilizing flow-based models as decision-making policies in reinforcement learning due to their high expressive capacity. However, effectively leveraging this expressivity for value maximization remains…

Machine Learning · Computer Science 2026-05-14 JaeHyeok Doo , Byeongguk Jeon , Seonghyeon Ye , Kimin Lee , Minjoon Seo

Compared to on-policy counterparts, off-policy model-free deep reinforcement learning can improve data efficiency by repeatedly using the previously gathered data. However, off-policy learning becomes challenging when the discrepancy…

Machine Learning · Computer Science 2023-09-27 Baturay Saglam , Dogan C. Cicek , Furkan B. Mutlu , Suleyman S. Kozat

We present flow Q-learning (FQL), a simple and performant offline reinforcement learning (RL) method that leverages an expressive flow-matching policy to model arbitrarily complex action distributions in data. Training a flow policy with RL…

Machine Learning · Computer Science 2025-05-27 Seohong Park , Qiyang Li , Sergey Levine

We consider the continuous-time Linear-Quadratic-Regulator (LQR) problem in terms of optimizing a real-valued matrix function over the set of feedback gains. The results developed are in parallel to those in Bu et al. [1] for discrete-time…

Systems and Control · Electrical Eng. & Systems 2020-06-17 Jingjing Bu , Afshin Mesbahi , Mehran Mesbahi

Diffusion Q-Learning (DQL) has established diffusion policies as a high-performing paradigm for offline reinforcement learning, but its reliance on multi-step denoising for action generation renders both training and inference slow and…

Machine Learning · Computer Science 2026-02-25 Thanh Nguyen , Chang D. Yoo

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.…

Machine Learning · Computer Science 2021-06-25 Ben Hambly , Renyuan Xu , Huining Yang

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…

Optimization and Control · Mathematics 2024-04-19 Xinpei Zhang , Guangyan Jia

Offline reinforcement learning often relies on behavior regularization that enforces policies to remain close to the dataset distribution. However, such approaches fail to distinguish between high-value and low-value actions in their…

Generative policies based on expressive model classes, such as diffusion and flow matching, are well-suited to complex control problems with highly multimodal action distributions. Their expressivity, however, comes at a significant…

Machine Learning · Computer Science 2026-05-13 Christos Ziakas , Alessandra Russo , Avishek Joey Bose

Most prior approaches to offline reinforcement learning (RL) have taken an iterative actor-critic approach involving off-policy evaluation. In this paper we show that simply doing one step of constrained/regularized policy improvement using…

Machine Learning · Computer Science 2021-12-06 David Brandfonbrener , William F. Whitney , Rajesh Ranganath , Joan Bruna

Q-learning is a stochastic approximation version of the classic value iteration. The literature has established that Q-learning suffers from both maximization bias and slower convergence. Recently, multi-step algorithms have shown practical…

Machine Learning · Computer Science 2024-07-03 Antony Vijesh , Shreyas S R

Direct policy gradient methods for reinforcement learning and continuous control problems are a popular approach for a variety of reasons: 1) they are easy to implement without explicit knowledge of the underlying model 2) they are an…

Machine Learning · Computer Science 2019-03-26 Maryam Fazel , Rong Ge , Sham M. Kakade , Mehran Mesbahi

Q-learning is widely used algorithm in reinforcement learning community. Under the lookup table setting, its convergence is well established. However, its behavior is known to be unstable with the linear function approximation case. This…

Machine Learning · Computer Science 2025-02-11 Han-Dong Lim , Donghwan Lee

As with any machine learning problem with limited data, effective offline RL algorithms require careful regularization to avoid overfitting. One-step methods perform regularization by doing just a single step of policy improvement, while…

Machine Learning · Computer Science 2023-07-25 Benjamin Eysenbach , Matthieu Geist , Sergey Levine , Ruslan Salakhutdinov

This paper revisits and extends the convergence and robustness properties of value and policy iteration algorithms for discrete-time linear quadratic regulator problems. In the model-based case, we extend current results concerning the…

Systems and Control · Electrical Eng. & Systems 2025-04-11 Bowen Song , Chenxuan Wu , Andrea Iannelli

The $Q$-learning algorithm is a simple and widely-used stochastic approximation scheme for reinforcement learning, but the basic protocol can exhibit instability in conjunction with function approximation. Such instability can be observed…

Machine Learning · Computer Science 2022-06-03 Andrea Zanette , Martin J. Wainwright

Off-policy learning refers to the problem of learning the value function of a way of behaving, or policy, while following a different policy. Gradient-based off-policy learning algorithms, such as GTD and TDC/GQ, converge even when using…

Artificial Intelligence · Computer Science 2015-12-15 Lucas Lehnert , Doina Precup

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…

Optimization and Control · Mathematics 2021-03-16 Bo Pang , Zhong-Ping Jiang

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
‹ Prev 1 2 3 10 Next ›