English
Related papers

Related papers: Provably Convergent Policy Optimization via Metric…

200 papers

We present a Distributionally Robust Optimization (DRO) approach to estimate a robustified regression plane in a linear regression setting, when the observed samples are potentially contaminated with adversarially corrupted outliers. Our…

Machine Learning · Statistics 2018-05-14 Ruidi Chen , Ioannis Ch. Paschalidis

Entropic regularization provides a simple way to approximate linear programs whose constraints split into two or more tractable blocks. The resulting objectives are amenable to cyclic Kullback-Leibler (KL) Bregman projections, with…

Optimization and Control · Mathematics 2026-05-11 Gabriel Peyré

Mirror descent (MD), a well-known first-order method in constrained convex optimization, has recently been shown as an important tool to analyze trust-region algorithms in reinforcement learning (RL). However, there remains a considerable…

Machine Learning · Computer Science 2021-06-08 Manan Tomar , Lior Shani , Yonathan Efroni , Mohammad Ghavamzadeh

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…

An optimal feedback controller for a given Markov decision process (MDP) can in principle be synthesized by value or policy iteration. However, if the system dynamics and the reward function are unknown, a learning agent must discover an…

Machine Learning · Computer Science 2019-07-19 Boris Belousov , Jan Peters

Safe Reinforcement Learning (RL) often faces significant issues such as constraint violations and instability, necessitating the use of constrained policy optimization, which seeks optimal policies while ensuring adherence to specific…

Machine Learning · Computer Science 2025-08-07 Ning Yang , Pengyu Wang , Guoqing Liu , Haifeng Zhang , Pin Lv , Jun Wang

Modern policy optimization methods in reinforcement learning, such as TRPO and PPO, owe their success to the use of parameterized policies. However, while theoretical guarantees have been established for this class of algorithms, especially…

Machine Learning · Statistics 2024-02-14 Carlo Alfano , Rui Yuan , Patrick Rebeschini

Safe policy improvement (SPI) offers theoretical control over policy updates, yet existing guarantees largely concern offline, tabular reinforcement learning (RL). We study SPI in general online settings, when combined with world model and…

Machine Learning · Computer Science 2026-01-29 Florent Delgrange , Raphael Avalos , Willem Röpke

Bayesian optimisation (BO) is a surrogate-based optimisation technique that efficiently solves expensive black-box functions with small evaluation budgets. Recent studies consider trust regions to improve the scalability of BO approaches…

Neural and Evolutionary Computing · Computer Science 2025-11-04 Kokila Kasuni Perera , Frank Neumann , Aneta Neumann

Bayesian optimization (BO) for high-dimensional constrained problems remains a significant challenge due to the curse of dimensionality. We propose Local Constrained Bayesian Optimization (LCBO), a novel framework tailored for such…

Machine Learning · Statistics 2026-03-10 Jing Jingzhe , Fan Zheyi , Szu Hui Ng , Qingpei Hu

We develop Distributionally Robust Optimization (DRO) formulations for Multivariate Linear Regression (MLR) and Multiclass Logistic Regression (MLG) when both the covariates and responses/labels may be contaminated by outliers. The DRO…

Machine Learning · Statistics 2020-06-12 Ruidi Chen , Ioannis Ch. Paschalidis

In this paper, we study a few challenging theoretical and numerical issues on the well known trust region policy optimization for deep reinforcement learning. The goal is to find a policy that maximizes the total expected reward when the…

Optimization and Control · Mathematics 2019-11-27 Mingming Zhao , Yongfeng Li , Zaiwen Wen

A novel optimization approach is proposed for application to policy gradient methods and evolution strategies for reinforcement learning (RL). The procedure uses a computationally efficient Wasserstein natural gradient (WNG) descent that…

Machine Learning · Computer Science 2021-03-19 Ted Moskovitz , Michael Arbel , Ferenc Huszar , Arthur Gretton

Among on-policy reinforcement learning algorithms, Proximal Policy Optimization (PPO) demonstrates is widely favored for its simplicity, numerical stability, and strong empirical performance. Standard PPO relies on surrogate objectives…

Machine Learning · Computer Science 2026-02-03 Shunpeng Yang , Ben Liu , Hua Chen

Safety exploration can be regarded as a constrained Markov decision problem where the expected long-term cost is constrained. Previous off-policy algorithms convert the constrained optimization problem into the corresponding unconstrained…

Machine Learning · Computer Science 2024-10-28 Hengrui Zhang , Youfang Lin , Sheng Han , Shuo Wang , Kai Lv

Reinforcement learning has significantly enhanced the reasoning capabilities of Large Language Models (LLMs) in complex problem-solving tasks. Recently, the introduction of DeepSeek R1 has inspired a surge of interest in leveraging…

Machine Learning · Computer Science 2025-08-07 Jinghang Han , Jiawei Chen , Hang Shao , Hao Ma , Mingcheng Li , Xintian Shen , Lihao Zheng , Wei Chen , Tao Wei , Lihua Zhang

The predict-then-optimize (PTO) framework is indispensable for addressing practical stochastic decision-making tasks. It consists of two crucial steps: initially predicting unknown parameters of an optimization model and subsequently…

Systems and Control · Electrical Eng. & Systems 2024-11-20 Jixian Liu , Tao Xu , Jianping He , Chongrong Fang

We consider the problem of constructing a least conservative estimator of the expected value $\mu$ of a non-negative heavy-tailed random variable. We require that the probability of overestimating the expected value $\mu$ is kept…

Optimization and Control · Mathematics 2026-04-21 Bart P. G. van Parys , Bert Zwart

Provably efficient Model-Based Reinforcement Learning (MBRL) based on optimism or posterior sampling (PSRL) is ensured to attain the global optimality asymptotically by introducing the complexity measure of the model. However, the…

Machine Learning · Computer Science 2022-09-19 Shenao Zhang

This paper studies a class of multiagent stochastic optimization problems where the objective is to minimize the expected value of a function which depends on a random variable. The probability distribution of the random variable is unknown…

Optimization and Control · Mathematics 2018-12-18 Ashish Cherukuri , Jorge Cortes