English
Related papers

Related papers: Bregman Gradient Policy Optimization

200 papers

We introduce a dynamic sparse training algorithm based on linearized Bregman iterations / mirror descent that exploits the naturally incurred sparsity by alternating between periods of static and dynamic sparsity pattern updates. The key…

Machine Learning · Computer Science 2026-05-19 Yannick Lunk , Sebastian J. Scott , Leon Bungert

We propose a learning framework based on stochastic Bregman iterations, also known as mirror descent, to train sparse neural networks with an inverse scale space approach. We derive a baseline algorithm called LinBreg, an accelerated…

Machine Learning · Computer Science 2022-08-16 Leon Bungert , Tim Roith , Daniel Tenbrinck , Martin Burger

The recent remarkable progress of deep reinforcement learning (DRL) stands on regularization of policy for stable and efficient learning. A popular method, named proximal policy optimization (PPO), has been introduced for this purpose. PPO…

Machine Learning · Computer Science 2023-07-04 Taisuke Kobayashi

We devise a control-theoretic reinforcement learning approach to support direct learning of the optimal policy. We establish various theoretical properties of our approach, such as convergence and optimality of our analog of the Bellman…

Machine Learning · Computer Science 2026-04-01 Weiqin Chen , Mark S. Squillante , Chai Wah Wu , Santiago Paternain

In this paper, we propose a provably convergent and practical framework for multi-objective reinforcement learning with max-min criterion. From a game-theoretic perspective, we reformulate max-min multi-objective reinforcement learning as a…

Machine Learning · Computer Science 2025-10-24 Woohyeon Byeon , Giseung Park , Jongseong Chae , Amir Leshem , Youngchul Sung

Post-training plays a crucial role in refining and aligning large language models to meet specific tasks and human preferences. While recent advancements in post-training techniques, such as Group Relative Policy Optimization (GRPO),…

Artificial Intelligence · Computer Science 2025-10-28 Kaichen Zhang , Yuzhong Hong , Junwei Bao , Hongfei Jiang , Yang Song , Dingqian Hong , Hui Xiong

In this paper, we propose some accelerated methods for solving optimization problems under the condition of relatively smooth and relatively Lipschitz continuous functions with an inexact oracle. We consider the problem of minimizing the…

Optimization and Control · Mathematics 2024-11-27 O. S. Savchuk , M. S. Alkousa , A. S. Shushko , A. A. Vyguzov , F. S. Stonyakin , D. A. Pasechnyuk , A. V. Gasnikov

We introduce the receding-horizon policy gradient (RHPG) algorithm, the first PG algorithm with provable global convergence in learning the optimal linear estimator designs, i.e., the Kalman filter (KF). Notably, the RHPG algorithm does not…

Optimization and Control · Mathematics 2023-09-12 Xiangyuan Zhang , Saviz Mowlavi , Mouhacine Benosman , Tamer Başar

In this paper, we analyze the local convergence rate of optimistic mirror descent methods in stochastic variational inequalities, a class of optimization problems with important applications to learning theory and machine learning. Our…

Optimization and Control · Mathematics 2021-07-06 Waïss Azizian , Franck Iutzeler , Jérôme Malick , Panayotis Mertikopoulos

While reinforcement learning has advanced the alignment of text-to-image (T2I) models, state-of-the-art policy gradient methods are still hampered by training instability and high variance, hindering convergence speed and compromising image…

Computer Vision and Pattern Recognition · Computer Science 2026-02-25 Jeongjae Lee , Jong Chul Ye

In this paper, we consider the online proximal mirror descent for solving the time-varying composite optimization problems. For various applications, the algorithm naturally involves the errors in the gradient and proximal operator. We…

Optimization and Control · Mathematics 2023-04-11 Woocheol Choi , Myeong-Su Lee , Seok-Bae Yun

Proximal Policy Optimization (PPO) is among the most widely used deep reinforcement learning algorithms, yet its theoretical foundations remain incomplete. Most importantly, convergence and understanding of fundamental PPO advantages remain…

Machine Learning · Computer Science 2026-02-04 Leif Doering , Daniel Schmidt , Moritz Melcher , Sebastian Kassing , Benedikt Wille , Tilman Aach , Simon Weissmann

We study the problem of computing an optimal policy of an infinite-horizon discounted constrained Markov decision process (constrained MDP). Despite the popularity of Lagrangian-based policy search methods used in practice, the oscillation…

Optimization and Control · Mathematics 2024-01-18 Dongsheng Ding , Chen-Yu Wei , Kaiqing Zhang , Alejandro Ribeiro

Interest in derivative-free optimization (DFO) and "evolutionary strategies" (ES) has recently surged in the Reinforcement Learning (RL) community, with growing evidence that they can match state of the art methods for policy optimization…

Recent advances in large language models (LLMs) have shown that reasoning ability can be significantly enhanced through Reinforcement Learning with Verifiable Rewards (RLVR). Group Relative Policy Optimization (GRPO) has emerged as the de…

Computation and Language · Computer Science 2025-10-13 Jingyu Zhou , Lu Ma , Hao Liang , Chengyu Shen , Bin Cui , Wentao Zhang

Policy gradient methods, which have been extensively studied in the last decade, offer an effective and efficient framework for reinforcement learning problems. However, their performances can often be unsatisfactory, suffering from…

Machine Learning · Computer Science 2026-01-27 Shihab Ahmed , El Houcine Bergou , Aritra Dutta , Yue Wang

We develop a new variational approach on level sets aiming towards convergence rate analysis of a variable Bregman proximal gradient (VBPG) method for a broad class of nonsmooth and nonconvex optimization problems. With this new approach,…

Optimization and Control · Mathematics 2019-09-05 Daoli Zhu , Sien Deng

A key aspect of Safe Reinforcement Learning (Safe RL) involves estimating the constraint condition for the next policy, which is crucial for guiding the optimization of safe policy updates. However, the existing Advantage-based Estimation…

Machine Learning · Computer Science 2024-12-17 Juntao Dai , Yaodong Yang , Qian Zheng , Gang Pan

Due to the high variance of policy gradients, on-policy optimization algorithms are plagued with low sample efficiency. In this work, we propose Augment-Reinforce-Merge (ARM) policy gradient estimator as an unbiased low-variance alternative…

Machine Learning · Computer Science 2019-03-14 Yunhao Tang , Mingzhang Yin , Mingyuan Zhou

In this paper we consider convergence rate problems for stochastic strongly-convex optimization in the non-Euclidean sense with a constraint set over a time-varying multi-agent network. We propose two efficient non-Euclidean stochastic…

Optimization and Control · Mathematics 2018-08-23 Deming Yuan , Yiguang Hong , Daniel W. C. Ho , Guoping Jiang