English
Related papers

Related papers: Bregman Gradient Policy Optimization

200 papers

Hybrid Group Relative Policy Optimization (Hybrid GRPO) is a reinforcement learning framework that extends Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO) by incorporating empirical multi-sample action…

Machine Learning · Computer Science 2025-02-05 Soham Sane

Most of the policy evaluation algorithms are based on the theories of Bellman Expectation and Optimality Equation, which derive two popular approaches - Policy Iteration (PI) and Value Iteration (VI). However, multi-step bootstrapping is…

Machine Learning · Computer Science 2021-12-16 Yuhui Wang , Qingyuan Wu , Pengcheng He , Xiaoyang Tan

Reinforcement learning is essential for neural architecture search and hyperparameter optimization, but the conventional approaches impede widespread use due to prohibitive time and computational costs. Inspired by DeepSeek-V3 multi-token…

Machine Learning · Computer Science 2025-06-19 Zheng Li , Jerry Cheng , Huanying Helen Gu

This work studies reinforcement learning (RL) in the context of multi-period supply chains subject to constraints, e.g., on production and inventory. We introduce Distributional Constrained Policy Optimization (DCPO), a novel approach for…

Machine Learning · Computer Science 2023-02-06 Jaime Sabal Bermúdez , Antonio del Rio Chanona , Calvin Tsay

We introduce the Pontryagin-Guided Direct Policy Optimization (PG-DPO) framework for high-dimensional continuous-time portfolio choice. Our approach combines Pontryagin's Maximum Principle (PMP) with backpropagation through time (BPTT) to…

Portfolio Management · Quantitative Finance 2025-09-12 Jeonggyu Huh , Jaegi Jeon , Hyeng Keun Koo , Byung Hwa Lim

The Group Relative Policy Optimization (GRPO), a reinforcement learning method used to fine-tune large language models (LLMs), has proved its effectiveness in practical applications such as DeepSeek-R1. It raises a question whether GRPO can…

Machine Learning · Computer Science 2025-11-20 Yanchen Xu , Ziheng Jiao , Hongyuan Zhang , Xuelong Li

Reinforcement learning considers the problem of finding policies that maximize an expected cumulative reward in a Markov decision process with unknown transition probabilities. In this paper we consider the problem of finding optimal…

Machine Learning · Computer Science 2020-10-19 Santiago Paternain , Juan Andres Bazerque , Alejandro Ribeiro

In this work, we show that natural policy gradient, a core algorithm in reinforcement learning, admits an exact formulation as a smoothed and averaged form of policy iteration. Specifically, we introduce doubly smoothed policy iteration…

Machine Learning · Computer Science 2026-05-12 Phalguni Nanda , Zaiwei Chen

Segmentation is a fundamental task in computer vision, underpinning pixel-level scene understanding and serving as a cornerstone for applications ranging from autonomous perception to medical image analysis. For complex referring…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Mario Markov , Stefan Maria Ailuro , Mohammad Mahdi , Luc Van Gool , Danda Pani Paudel

In this paper we study consensus-based optimization (CBO), a versatile, flexible and customizable optimization method suitable for performing nonconvex and nonsmooth global optimizations in high dimensions. CBO is a multi-particle…

Numerical Analysis · Mathematics 2026-05-28 Konstantin Riedl

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

Guided policy search algorithms can be used to optimize complex nonlinear policies, such as deep neural networks, without directly computing policy gradients in the high-dimensional parameter space. Instead, these methods use supervised…

Machine Learning · Computer Science 2016-07-18 William Montgomery , Sergey Levine

Policy gradient methods are reinforcement learning algorithms that adapt a parameterized policy by following a performance gradient estimate. Conventional policy gradient methods use Monte-Carlo techniques to estimate the gradient, which…

Machine Learning · Computer Science 2026-05-01 Mohammad Ghavamzadeh , Yaakov Engel , Michal Valko

A typical assumption for the analysis of first order optimization methods is the Lipschitz continuity of the gradient of the objective function. However, for many practical applications this assumption is violated, including loss functions…

Optimization and Control · Mathematics 2019-10-10 Mahesh Chandra Mukkamala , Felix Westerkamp , Emanuel Laude , Daniel Cremers , Peter Ochs

We develop Policy Gradient with Second-Order Momentum (PG-SOM), a lightweight second-order optimisation scheme for reinforcement-learning policies. PG-SOM augments the classical REINFORCE update with two exponentially weighted statistics: a…

Machine Learning · Computer Science 2025-05-20 Tianyu Sun

Stochastic optimization algorithms, particularly stochastic policy gradient (SPG), report significant success in reinforcement learning (RL). Nevertheless, up to now, that how to speedily acquire an optimal solution for RL is still a…

Machine Learning · Computer Science 2024-05-22 Haobin Zhang , Zhuang Yang

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

We consider an improper reinforcement learning setting where a learner is given $M$ base controllers for an unknown Markov decision process, and wishes to combine them optimally to produce a potentially new controller that can outperform…

Machine Learning · Computer Science 2021-07-06 Mohammadi Zaki , Avinash Mohan , Aditya Gopalan , Shie Mannor

Existing Reinforcement Learning from Verifiable Rewards (RLVR) methods, such as Group Relative Policy Optimization (GRPO), have achieved remarkable progress in improving the reasoning capabilities of Large Reasoning Models (LRMs). However,…

Machine Learning · Computer Science 2026-04-16 Hsiu-Yuan Huang , Chenming Tang , Weijie Liu , Clive Bai , Saiyong Yang , Yunfang Wu

We study Concave Constrained Markov Decision Processes (Concave CMDPs) where both the objective and constraints are defined as concave functions of the state-action occupancy measure. We propose the Variance-Reduced Primal-Dual Policy…

Machine Learning · Computer Science 2024-05-28 Donghao Ying , Mengzi Amy Guo , Hyunin Lee , Yuhao Ding , Javad Lavaei , Zuo-Jun Max Shen