English
Related papers

Related papers: Global Convergence of Natural Policy Gradient with…

200 papers

Policy gradient methods have been frequently applied to problems in control and reinforcement learning with great success, yet existing convergence analysis still relies on non-intuitive, impractical and often opaque conditions. In…

Machine Learning · Computer Science 2022-04-08 Matthew S. Zhang , Murat A. Erdogdu , Animesh Garg

This paper presents a novel natural gradient and Hessian-free (NGHF) optimisation framework for neural network training that can operate efficiently in a distributed manner. It relies on the linear conjugate gradient (CG) algorithm to…

Machine Learning · Computer Science 2021-03-16 Adnan Haider , Chao Zhang , Florian L. Kreyssig , Philip C. Woodland

Sample inefficiency is a long-lasting problem in reinforcement learning (RL). The state-of-the-art estimates the optimal action values while it usually involves an extensive search over the state-action space and unstable optimization.…

Machine Learning · Computer Science 2019-11-27 Kaixiang Lin , Jiayu Zhou

We study the problem of robust reinforcement learning under adversarial corruption on both rewards and transitions. Our attack model assumes an \textit{adaptive} adversary who can arbitrarily corrupt the reward and transition at every step…

Machine Learning · Computer Science 2021-06-09 Xuezhou Zhang , Yiding Chen , Xiaojin Zhu , Wen Sun

Neural Network based approximations of the Value function make up the core of leading Policy Based methods such as Trust Regional Policy Optimization (TRPO) and Proximal Policy Optimization (PPO). While this adds significant value when…

Machine Learning · Computer Science 2024-06-03 Hari Srikanth

Newton's Method is widely used to find the solution of complex non-linear simulation problems in Computer Graphics. To guarantee a descent direction, it is common practice to clamp the negative eigenvalues of each element Hessian prior to…

Graphics · Computer Science 2026-05-26 José Antonio Fernández-Fernández , Fabian Löschner , Jan Bender

This paper deals with estimating model parameters in graphical models. We reformulate it as an information geometric optimization problem and introduce a natural gradient descent strategy that incorporates additional meta parameters. We…

Machine Learning · Computer Science 2019-05-15 Eric Benhamou , Jamal Atif , Rida Laraki , David Saltiel

The softmax policy gradient (PG) method, which performs gradient ascent under softmax policy parameterization, is arguably one of the de facto implementations of policy optimization in modern reinforcement learning. For $\gamma$-discounted…

Machine Learning · Computer Science 2022-12-19 Gen Li , Yuting Wei , Yuejie Chi , Yuxin Chen

We consider minimizing finite-sum and expectation objective functions via Hessian-averaging based subsampled Newton methods. These methods allow for gradient inexactness and have fixed per-iteration Hessian approximation costs. The recent…

Optimization and Control · Mathematics 2024-08-15 Thomas O'Leary-Roseberry , Raghu Bollapragada

Policy Gradient (PG) algorithms are among the best candidates for the much-anticipated applications of reinforcement learning to real-world control tasks, such as robotics. However, the trial-and-error nature of these methods poses safety…

Machine Learning · Computer Science 2022-06-20 Matteo Papini , Matteo Pirotta , Marcello Restelli

Entropy regularization is an important idea in reinforcement learning, with great success in recent algorithms like Soft Q Network (SQN) and Soft Actor-Critic (SAC1). In this work, we extend this idea into the on-policy realm. We propose…

Machine Learning · Computer Science 2020-10-19 Jingbin Liu , Xinyang Gu , Shuai Liu

A recent article introduced thecontinuous stochastic gradient method (CSG) for the efficient solution of a class of stochastic optimization problems. While the applicability of known stochastic gradient type methods is typically limited to…

Optimization and Control · Mathematics 2021-11-16 Lukas Pflug , Max Grieshammer , Andrian Uihlein , Michael Stingl

Reinforcement Learning (RL) has been used to finetune Large Language Models (LLMs) using a reward model trained from preference data, to better align with human judgment. The recently introduced direct alignment methods, which are often…

In this paper, we present the proximal-proximal-gradient method (PPG), a novel optimization method that is simple to implement and simple to parallelize. PPG generalizes the proximal-gradient method and ADMM and is applicable to…

Optimization and Control · Mathematics 2017-10-19 Ernest K. Ryu , Wotao Yin

We present a methodology to deploy the stochastic policy gradient method, using actor-critic techniques, when the optimal policy is approximated using a parametric optimization problem, allowing one to enforce safety via hard constraints.…

Systems and Control · Electrical Eng. & Systems 2024-09-23 Sebastien Gros , Mario Zanon

Finding Nash equilibria in two-player zero-sum imperfect-information games remains a central challenge in multi-agent reinforcement learning. Recent multi-round regularization methods offer a promising direction, yet existing approaches…

Machine Learning · Computer Science 2026-05-01 Eason Yu , Tzu Hao Liu , Clément L. Canonne , Yunke Wang , Chang Xu , Nguyen H. Tran , Stefano V. Albrecht

This paper presents a novel neural network training approach for faster convergence and better generalization abilities in deep reinforcement learning. Particularly, we focus on the enhancement of training and evaluation performance in…

Machine Learning · Computer Science 2020-05-26 Mohammed Sharafath Abdul Hameed , Gavneet Singh Chadha , Andreas Schwung , Steven X. Ding

In this paper, we propose World Model Policy Gradient (WMPG), an approach to reduce the variance of policy gradient estimates using learned world models (WM's). In WMPG, a WM is trained online and used to imagine trajectories. The imagined…

Machine Learning · Statistics 2020-10-30 Michal Nauman , Floris Den Hengst

We study the sample complexity of reducing reinforcement learning to a sequence of empirical risk minimization problems over the policy space. Such reductions-based algorithms exhibit local convergence in the function space, as opposed to…

Machine Learning · Computer Science 2023-01-26 Naman Agarwal , Brian Bullins , Karan Singh

In this work, a nonlinear momentum method is introduced to enhance the convergence performance of momentum-based gradient optimization algorithms. Classical momentum methods, such as the Heavy Ball method, can be viewed as a dynamical…

Computational Physics · Physics 2026-02-09 Jianing Zhang , Rumei Liu