English
Related papers

Related papers: Bregman Gradient Policy Optimization

200 papers

Group Relative Policy Optimization(GRPO) has become a cornerstone of modern reinforcement learning alignment, prized for its efficacy in foregoing an explicit value-critic by leveraging reward normalization across sampled trajectory…

Computation and Language · Computer Science 2026-05-29 Redacted by arXiv

We propose a metalearning approach for learning gradient-based reinforcement learning (RL) algorithms. The idea is to evolve a differentiable loss function, such that an agent, which optimizes its policy to minimize this loss, will achieve…

Machine Learning · Computer Science 2018-05-01 Rein Houthooft , Richard Y. Chen , Phillip Isola , Bradly C. Stadie , Filip Wolski , Jonathan Ho , Pieter Abbeel

Proximal policy optimization (PPO) is a widely-used algorithm for on-policy reinforcement learning. This work offers an alternative perspective of PPO, in which it is decomposed into the inner-loop estimation of update vectors, and the…

Machine Learning · Computer Science 2024-11-04 Charlie B. Tan , Edan Toledo , Benjamin Ellis , Jakob N. Foerster , Ferenc Huszár

In recent years, by using Bregman distance, the Lipschitz gradient continuity and strong convexity were lifted and replaced by relative smoothness and relative strong convexity. Under the mild assumptions, it was proved that gradient…

Optimization and Control · Mathematics 2022-06-22 Jian Chen , Liping Tang , Xinmin Yang

Policy gradient methods are among the most effective methods for large-scale reinforcement learning, and their empirical success has prompted several works that develop the foundation of their global convergence theory. However, prior works…

Machine Learning · Computer Science 2020-12-25 Junzi Zhang , Jongho Kim , Brendan O'Donoghue , Stephen Boyd

The Bregman proximal gradient method (BPGM), which uses the Bregman distance as a proximity measure in the iterative scheme, has recently been re-developed for minimizing convex composite problems without the global Lipschitz gradient…

Optimization and Control · Mathematics 2025-04-16 Lei Yang , Kim-Chuan Toh

Memory-efficient optimization methods have recently gained increasing attention for scaling full-parameter training of large language models under the GPU-memory bottleneck. Existing approaches either lack clear convergence guarantees, or…

Machine Learning · Computer Science 2026-03-11 Hui Yang , Tao Ren , Jinyang Jiang , Wan Tian , Yijie Peng

Model-based reinforcement learning approaches carry the promise of being data efficient. However, due to challenges in learning dynamics models that sufficiently match the real-world dynamics, they struggle to achieve the same asymptotic…

Machine Learning · Computer Science 2018-09-17 Ignasi Clavera , Jonas Rothfuss , John Schulman , Yasuhiro Fujita , Tamim Asfour , Pieter Abbeel

On-policy deep reinforcement learning algorithms have low data utilization and require significant experience for policy improvement. This paper proposes a proximal policy optimization algorithm with prioritized trajectory replay (PTR-PPO)…

Machine Learning · Computer Science 2021-12-09 Xingxing Liang , Yang Ma , Yanghe Feng , Zhong Liu

Projected policy gradient under the simplex parameterization, policy gradient and natural policy gradient under the softmax parameterization, are fundamental algorithms in reinforcement learning. There have been a flurry of recent…

Optimization and Control · Mathematics 2024-04-12 Jiacai Liu , Wenye Li , Ke Wei

We study a new two-time-scale stochastic gradient method for solving optimization problems, where the gradients are computed with the aid of an auxiliary variable under samples generated by time-varying MDPs controlled by the underlying…

Optimization and Control · Mathematics 2024-08-27 Sihan Zeng , Thinh T. Doan , Justin Romberg

As the most successful variant and improvement for Trust Region Policy Optimization (TRPO), proximal policy optimization (PPO) has been widely applied across various domains with several advantages: efficient data utilization, easy…

Machine Learning · Computer Science 2019-02-15 Xiangxiang Chu

Instability and slowness are two main problems in deep reinforcement learning. Even if proximal policy optimization (PPO) is the state of the art, it still suffers from these two problems. We introduce an improved algorithm based on…

Machine Learning · Computer Science 2019-10-01 Zhenyu Zhang , Xiangfeng Luo , Tong Liu , Shaorong Xie , Jianshu Wang , Wei Wang , Yang Li , Yan Peng

We consider the problem of Cost-Aware Learning, where sampling different component functions of a finite-sum objective incurs different costs. The objective is to reach a target error while minimizing the total cost. First, we propose the…

Machine Learning · Computer Science 2026-05-01 Clara Mohri , Amir Globerson , Haim Kaplan , Tomer Koren , Yishay Mansour

Proximal policy optimization and trust region policy optimization (PPO and TRPO) with actor and critic parametrized by neural networks achieve significant empirical success in deep reinforcement learning. However, due to nonconvexity, the…

Machine Learning · Computer Science 2023-03-01 Boyi Liu , Qi Cai , Zhuoran Yang , Zhaoran Wang

Distributed optimization aims to optimize a global objective formed by a sum of coupled local convex functions over a graph via only local computation and communication. In this paper, we propose the Bregman parallel direction method of…

Optimization and Control · Mathematics 2018-05-03 Yue Yu , Behçet Açıkmeşe , Mehran Mesbahi

Group Relative Policy Optimisation (GRPO) enhances large language models by estimating advantages across a group of sampled trajectories. However, mapping these trajectory-level advantages to policy updates requires aggregating token-level…

We consider stochastic gradient methods under the interpolation regime where a perfect fit can be obtained (minimum loss at each observation). While previous work highlighted the implicit regularization of such algorithms, we consider an…

Optimization and Control · Mathematics 2020-04-01 Anant Raj , Francis Bach

Policy Mirror Descent (PMD) is a popular framework in reinforcement learning, serving as a unifying perspective that encompasses numerous algorithms. These algorithms are derived through the selection of a mirror map and enjoy finite-time…

Machine Learning · Statistics 2026-01-07 Carlo Alfano , Sebastian Towers , Silvia Sapora , Chris Lu , Patrick Rebeschini

Modern meta-reinforcement learning (Meta-RL) methods are mainly developed based on model-agnostic meta-learning, which performs policy gradient steps across tasks to maximize policy performance. However, the gradient conflict problem is…

Artificial Intelligence · Computer Science 2022-09-22 Haozhi Wang , Qing Wang , Yunfeng Shao , Dong Li , Jianye Hao , Yinchuan Li
‹ Prev 1 8 9 10 Next ›