English
Related papers

Related papers: Beyond Exact Gradients: Convergence of Stochastic …

200 papers

We study robust Markov decision processes (RMDPs) with general policy parameterization under s-rectangular and non-rectangular uncertainty sets. Prior work is largely limited to tabular policies, and hence either lacks sample complexity…

Machine Learning · Computer Science 2026-02-13 Anirudh Satheesh , Ziyi Chen , Furong Huang , Heng Huang

Stochastic variance reduced methods have shown strong performance in solving finite-sum problems. However, these methods usually require the users to manually tune the step-size, which is time-consuming or even infeasible for some…

Optimization and Control · Mathematics 2023-10-10 Binghui Xie , Chenhan Jin , Kaiwen Zhou , James Cheng , Wei Meng

We propose an extragradient method with stepsizes bounded away from zero for stochastic variational inequalities requiring only pseudo-monotonicity. We provide convergence and complexity analysis, allowing for an unbounded feasible set,…

Optimization and Control · Mathematics 2017-03-02 Alfredo Iusem , Alejandro Jofré , Roberto I. Oliveira , Philip Thompson

Following [21, 23], the present work investigates a new relative entropy-regularized algorithm for solving the optimal transport on a graph problem within the randomized shortest paths formalism. More precisely, a unit flow is injected into…

Machine Learning · Computer Science 2021-09-21 Sylvain Courtain , Guillaume Guex , Ilkka Kivimaki , Marco Saerens

Reinforcement learning (RL) has become a key driver of language model reasoning. Among RL algorithms, Group Relative Policy Optimization (GRPO) is the de facto standard, avoiding the need for a critic by using per-prompt baselines and…

Machine Learning · Computer Science 2026-02-02 Cheng Ge , Caitlyn Heqi Yin , Hao Liang , Jiawei Zhang

We propose expected policy gradients (EPG), which unify stochastic policy gradients (SPG) and deterministic policy gradients (DPG) for reinforcement learning. Inspired by expected sarsa, EPG integrates (or sums) across actions when…

Machine Learning · Statistics 2020-05-05 Kamil Ciosek , Shimon Whiteson

Deep Reinforcement Learning (Deep RL) has been receiving increasingly more attention thanks to its encouraging performance on a variety of control tasks. Yet, conventional regularization techniques in training neural networks (e.g., $L_2$…

Machine Learning · Computer Science 2021-11-30 Zhuang Liu , Xuanlin Li , Bingyi Kang , Trevor Darrell

Sample-based trajectory optimisers are a promising tool for the control of robotics with non-differentiable dynamics and cost functions. Contemporary approaches derive from a restricted subclass of stochastic optimal control where the…

Robotics · Computer Science 2021-10-07 Tom Lefebvre , Guillaume Crevecoeur

We study the problem of efficiently estimating policies that simultaneously optimize multiple objectives in reinforcement learning (RL). Given $n$ objectives (or tasks), we seek the optimal partition of these objectives into $k \ll n$…

Machine Learning · Computer Science 2026-02-24 Zhenshuo Zhang , Minxuan Duan , Youran Ye , Hongyang R. Zhang

Large language model (LLM) alignment via reinforcement learning from human preferences (RLHF) suffers from unstable policy updates, ambiguous gradient directions, poor interpretability, and high gradient variance in mainstream pairwise…

Machine Learning · Computer Science 2026-05-12 Hao Yu

Reinforcement learning with verifiable rewards (RLVR) has become a practical route to improve large language model reasoning, and Group Relative Policy Optimization (GRPO) is a widely used optimizer in this setting. However, RLVR training…

Machine Learning · Computer Science 2026-05-14 Tue Le , Linh Ngo Van , Trung Le

We consider the problem of estimating a probability distribution that maximizes the entropy while satisfying a finite number of moment constraints, possibly corrupted by noise. Based on duality of convex programming, we present a novel…

Optimization and Control · Mathematics 2019-10-22 Tobias Sutter , David Sutter , Peyman Mohajerin Esfahani , John Lygeros

In this paper, we propose a new algorithm PPG (Proximal Policy Gradient), which is close to both VPG (vanilla policy gradient) and PPO (proximal policy optimization). The PPG objective is a partial variation of the VPG objective and the…

Machine Learning · Computer Science 2020-10-21 Ju-Seung Byun , Byungmoon Kim , Huamin Wang

While the idea of robust dynamic programming (DP) is compelling for systems affected by uncertainty, addressing worst-case disturbances generally results in excessive conservatism. This paper introduces a method for constructing control…

Systems and Control · Electrical Eng. & Systems 2025-05-19 Menno van Zutphen , Domagoj Herceg , Duarte J. Antunes

Robust Markov decision processes (RMDPs) provide a promising framework for computing reliable policies in the face of model errors. Many successful reinforcement learning algorithms build on variations of policy-gradient methods, but…

Machine Learning · Computer Science 2024-05-15 Qiuhao Wang , Chin Pang Ho , Marek Petrik

This paper is devoted to first-order algorithms for smooth convex optimization with inexact gradients. Unlike the majority of the literature on this topic, we consider the setting of relative rather than absolute inexactness. More…

Optimization and Control · Mathematics 2023-10-03 Nikita Kornilov , Eduard Gorbunov , Mohammad Alkousa , Fedor Stonyakin , Pavel Dvurechensky , Alexander Gasnikov

In this work, we consider policy-based methods for solving the reinforcement learning problem, and establish the sample complexity guarantees. A policy-based algorithm typically consists of an actor and a critic. We consider using various…

Machine Learning · Computer Science 2023-01-16 Zaiwei Chen , Siva Theja Maguluri

Regularization of control policies using entropy can be instrumental in adjusting predictability of real-world systems. Applications benefiting from such approaches range from, e.g., cybersecurity, which aims at maximal unpredictability, to…

Systems and Control · Electrical Eng. & Systems 2026-02-18 Menno van Zutphen , Giannis Delimpaltadakis , Maurice Heemels , Duarte Antunes

The advancement of Large Reasoning Models (LRMs) has catalyzed a paradigm shift from reactive ``fast thinking'' text generation to systematic, step-by-step ``slow thinking'' reasoning, unlocking state-of-the-art performance in complex…

Artificial Intelligence · Computer Science 2026-05-25 Junyao Yang , Chen Qian , Kun Wang , Linfeng Zhang , Quanshi Zhang , Yong Liu , Dongrui Liu

Deep Reinforcement Learning (Deep RL) has had incredible achievements on high dimensional problems, yet its learning process remains unstable even on the simplest tasks. Deep RL uses neural networks as function approximators. These neural…

Machine Learning · Computer Science 2022-10-18 Riccardo Della Vecchia , Alena Shilova , Philippe Preux , Riad Akrour