English
Related papers

Related papers: Quasi-Newton Trust Region Policy Optimization

200 papers

Tuning step sizes is crucial for the stability and efficiency of optimization algorithms. While adaptive coordinate-wise step sizes have been shown to outperform scalar step size in first-order methods, their use in second-order methods is…

Machine Learning · Computer Science 2025-05-20 Wei Lin , Qingyu Song , Hong Xu

Since its introduction a decade ago, \emph{relative entropy policy search} (REPS) has demonstrated successful policy learning on a number of simulated and real-world robotic domains, not to mention providing algorithmic components used by…

Machine Learning · Computer Science 2021-03-18 Aldo Pacchiano , Jonathan Lee , Peter Bartlett , Ofir Nachum

In recent years, trust region on-policy reinforcement learning has achieved impressive results in addressing complex control tasks and gaming scenarios. However, contemporary state-of-the-art algorithms within this category primarily…

Machine Learning · Computer Science 2024-05-31 Weiye Zhao , Feihan Li , Yifan Sun , Rui Chen , Tianhao Wei , Changliu Liu

In safety-critical domains, reinforcement learning (RL) agents must often satisfy strict, zero-cost safety constraints while accomplishing tasks. Existing model-free methods frequently either fail to achieve near-zero safety violations or…

Machine Learning · Computer Science 2026-05-11 Dominik Wagner , Ankit Kanwar , Luke Ong

In this paper, we develop and analyze sub-sampled trust-region methods for solving finite-sum optimization problems. These methods employ subsampling strategies to approximate the gradient and Hessian of the objective function,…

Optimization and Control · Mathematics 2025-07-24 Max L. N. Goncalves , Geovani N. Grapiglia

Quasi-Newton methods are widely used for solving convex optimization problems due to their ease of implementation, practical efficiency, and strong local convergence guarantees. However, their global convergence is typically established…

Optimization and Control · Mathematics 2025-08-28 Artem Agafonov , Vladislav Ryspayev , Samuel Horváth , Alexander Gasnikov , Martin Takáč , Slavomir Hanzely

Building upon the recent success of deep reinforcement learning methods, we investigate the possibility of on-policy reinforcement learning improvement by reusing the data from several consecutive policies. On-policy methods bring many…

Machine Learning · Computer Science 2019-01-21 Dmitry Kangin , Nicolas Pugeault

In this work, we introduce a novel stochastic second-order method, within the framework of a non-monotone trust-region approach, for solving the unconstrained, nonlinear, and non-convex optimization problems arising in the training of deep…

Optimization and Control · Mathematics 2024-01-18 Natasa Krejic , Natasa Krklec Jerinkic , Angeles Martinez , Mahsa Yousefi

In this paper, we propose several new stochastic second-order algorithms for policy optimization that only require gradient and Hessian-vector product in each iteration, making them computationally efficient and comparable to policy…

Optimization and Control · Mathematics 2023-01-31 Jinsong Liu , Chenghan Xie , Qi Deng , Dongdong Ge , Yinyu Ye

We introduce a variant of the proximal gradient method in which the quadratic term is diagonal but may be indefinite, and is safeguarded by a trust region. Our method is a special case of the proximal quasi-Newton trust-region method of…

Optimization and Control · Mathematics 2023-09-18 Geoffroy Leconte , Dominique Orban

In Part I of this work, we have proposed a general framework of decentralized stochastic quasi-Newton methods, which converge linearly to the optimal solution under the assumption that the local Hessian inverse approximations have bounded…

Optimization and Control · Mathematics 2022-01-20 Jiaojiao Zhang , Huikang Liu , Anthony Man-Cho So , Qing Ling

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

The trust-region (TR) method is renowned historically for its robustness in nonconvex problems and extraordinary numerical performance, but the study of its performance in convex optimization is somehow limited. This paper complements the…

Optimization and Control · Mathematics 2026-01-26 Yuntian Jiang , Chang He , Chuwen Zhang , Dongdong Ge , Bo Jiang , Yinyu Ye

Reinforcement learning (RL) has become a cornerstone for fine-tuning Large Language Models (LLMs), with Proximal Policy Optimization (PPO) serving as the de facto standard algorithm. Despite its ubiquity, we argue that the core ratio…

Machine Learning · Computer Science 2026-05-27 Penghui Qi , Xiangxin Zhou , Zichen Liu , Tianyu Pang , Chao Du , Min Lin , Wee Sun Lee

In this work, we propose to apply trust region optimization to deep reinforcement learning using a recently proposed Kronecker-factored approximation to the curvature. We extend the framework of natural policy gradient and propose to…

Machine Learning · Computer Science 2017-08-21 Yuhuai Wu , Elman Mansimov , Shun Liao , Roger Grosse , Jimmy Ba

Natural policy gradient (NPG) and its variants are widely-used policy search methods in reinforcement learning. Inspired by prior work, a new NPG variant coined NPG-HM is developed in this paper, which utilizes the Hessian-aided momentum…

Machine Learning · Computer Science 2024-01-23 Jie Feng , Ke Wei , Jinchi Chen

We consider the problem of control in the setting of reinforcement learning (RL), where model information is not available. Policy gradient algorithms are a popular solution approach for this problem and are usually shown to converge to a…

Machine Learning · Computer Science 2023-04-24 Mizhaan Prajit Maniyar , Akash Mondal , Prashanth L. A. , Shalabh Bhatnagar

In recent years, various subspace algorithms have been developed to handle large-scale optimization problems. Although existing subspace Newton methods require fewer iterations to converge in practice, the matrix operations and full…

Optimization and Control · Mathematics 2024-06-05 Taisei Miyaishi , Ryota Nozawa , Pierre-Louis Poirion , Akiko Takeda

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

Policy gradient methods are an appealing approach in reinforcement learning because they directly optimize the cumulative reward and can straightforwardly be used with nonlinear function approximators such as neural networks. The two main…

Machine Learning · Computer Science 2018-10-23 John Schulman , Philipp Moritz , Sergey Levine , Michael Jordan , Pieter Abbeel