English
Related papers

Related papers: Provably Convergent Policy Optimization via Metric…

200 papers

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

This paper considers a convex composite optimization problem with affine constraints, which includes problems that take the form of minimizing a smooth convex objective function over the intersection of (simple) convex sets, or regularized…

Optimization and Control · Mathematics 2023-02-23 Dan Garber , Tsur Livney , Shoham Sabach

In many real-world applications, ensuring the robustness and stability of deep neural networks (DNNs) is crucial, particularly for image classification tasks that encounter various input perturbations. While data augmentation techniques…

Machine Learning · Statistics 2025-06-26 Jiaming Hu , Debarghya Mukherjee , Ioannis Ch. Paschalidis

Reinforcement Learning with Verifiable Rewards (RLVR) is increasingly viewed as a tree pruning mechanism. However, we identify a systemic pathology termed Recursive Space Contraction (RSC), an irreversible collapse driven by the combined…

Artificial Intelligence · Computer Science 2026-02-06 Tianyi Wang , Long Li , Hongcan Guo , Yibiao Chen , Yixia Li , Yong Wang , Yun Chen , Guanhua Chen

By leveraging differentiable dynamics, Reparameterization Policy Gradient (RPG) achieves high sample efficiency. However, current approaches are hindered by two critical limitations: the under-utilization of computationally expensive…

Machine Learning · Computer Science 2026-02-09 Hai Zhong , Xun Wang , Zhuoran Li , Longbo Huang

Sinkhorn divergence is a measure of dissimilarity between two probability measures. It is obtained through adding an entropic regularization term to Kantorovich's optimal transport problem and can hence be viewed as an entropically…

Numerical Analysis · Mathematics 2020-05-01 Mohammad Motamed

Proximal policy optimization(PPO) has been proposed as a first-order optimization method for reinforcement learning. We should notice that an exterior penalty method is used in it. Often, the minimizers of the exterior penalty functions…

Machine Learning · Computer Science 2018-12-18 Cheng Zeng , Hongming Zhang

Distributionally robust stochastic optimization (DRSO) is an approach to optimization under uncertainty in which, instead of assuming that there is a known true underlying probability distribution, one hedges against a chosen set of…

Optimization and Control · Mathematics 2022-05-03 Rui Gao , Anton J. Kleywegt

Group Relative Policy Optimization (GRPO) was introduced and used recently for promoting reasoning in LLMs under verifiable (binary) rewards. We show that the mean + variance calibration of these rewards induces a weighted contrastive loss…

Machine Learning · Computer Science 2025-10-22 Youssef Mroueh

Constrained optimization is popularly seen in reinforcement learning for addressing complex control tasks. From the perspective of dynamic system, iteratively solving a constrained optimization problem can be framed as the temporal…

Machine Learning · Computer Science 2025-01-28 Tianqi Zhang , Puzhen Yuan , Guojian Zhan , Ziyu Lin , Yao Lyu , Zhenzhi Qin , Jingliang Duan , Liping Zhang , Shengbo Eben Li

This paper introduces two novel modifications to the Dynamic sAmpling Policy Optimization (DAPO) algorithm [1], approached from a mixed-policy perspective. Standard policy gradient methods can suffer from instability and sample…

Machine Learning · Computer Science 2025-08-20 Hongze Tan , Yuchen Li

Historically speaking, it is hard to balance the global and local efficiency of second-order optimization algorithms. For instance, the classical Newton's method possesses excellent local convergence but lacks global guarantees, often…

Optimization and Control · Mathematics 2025-11-11 Yuntian Jiang , Chuwen Zhang , Bo Jiang , Yinyu Ye

Most methods in reinforcement learning use a Policy Gradient (PG) approach to learn a parametric stochastic policy that maps states to actions. The standard approach is to implement such a mapping via a neural network (NN) whose parameters…

Machine Learning · Computer Science 2024-05-29 Sergio Rozada , Antonio G. Marques

Many reinforcement learning algorithms can be seen as versions of approximate policy iteration (API). While standard API often performs poorly, it has been shown that learning can be stabilized by regularizing each policy update by the…

Machine Learning · Computer Science 2021-02-15 Nevena Lazić , Botao Hao , Yasin Abbasi-Yadkori , Dale Schuurmans , Csaba Szepesvári

We study the factor model problem, which aims to uncover low-dimensional structures in high-dimensional datasets. Adopting a robust data-driven approach, we formulate the problem as a saddle-point optimization. Our primary contribution is a…

Optimization and Control · Mathematics 2026-04-13 Shabnam Khodakaramzadeh , Soroosh Shafiee , Gabriel de Albuquerque Gleizer , Peyman Mohajerin Esfahani

Reinforcement learning algorithms, though successful, tend to over-fit to training environments hampering their application to the real-world. This paper proposes $\text{W}\text{R}^{2}\text{L}$ -- a robust reinforcement learning algorithm…

Machine Learning · Computer Science 2019-09-18 Mohammed Amin Abdullah , Hang Ren , Haitham Bou Ammar , Vladimir Milenkovic , Rui Luo , Mingtian Zhang , Jun Wang

We propose to improve trust region policy search with normalizing flows policy. We illustrate that when the trust region is constructed by KL divergence constraints, normalizing flows policy generates samples far from the 'center' of the…

Artificial Intelligence · Computer Science 2019-02-04 Yunhao Tang , Shipra Agrawal

The Linear Quadratic Gaussian (LQG) regulator is a cornerstone of optimal control theory, yet its performance can degrade significantly when the noise distributions deviate from the assumed Gaussian model. To address this limitation, this…

Systems and Control · Electrical Eng. & Systems 2026-03-27 Riccardo Cescon , Andrea Martin , Giancarlo Ferrari-Trecate

Classical on-policy algorithms such as PPO and mirror descent policy optimization provide stable proximal policy updates through tractable action likelihoods, but are typically instantiated with simple Gaussian policies whose expressiveness…

Machine Learning · Computer Science 2026-05-29 Yuehu Gong , Zeyuan Wang , Yulin Chen , Shutong Ding , Qingyuan Zhou , Yanwei Fu

Reinforcement learning from human feedback (RLHF) has become a core post-training step for aligning large language models, yet the reward signal used in RLHF is only a learned proxy for true human utility. From an operations research…

Machine Learning · Computer Science 2026-05-19 Yikai Wang , Shang Liu , Jose Blanchet