中文
相关论文

相关论文: Neural Proximal/Trust Region Policy Optimization A…

200 篇论文

Parametric optimization solves a family of optimization problems as a function of parameters. It is a critical component in situations where optimal decision making is repeatedly performed for updated parameter values, but computation…

最优化与控制 · 数学 2023-08-22 Hyunglip Bae , Jang Ho Kim , Woo Chang Kim

The problem of constrained reinforcement learning (CRL) holds significant importance as it provides a framework for addressing critical safety satisfaction concerns in the field of reinforcement learning (RL). However, with the introduction…

机器学习 · 计算机科学 2023-05-24 Chengbin Xuan , Feng Zhang , Faliang Yin , Hak-Keung Lam

Natural policy gradient (NPG) is a common policy optimization algorithm and can be viewed as mirror ascent in the space of probabilities. Recently, Vaswani et al. [2021] introduced a policy gradient method that corresponds to mirror ascent…

机器学习 · 计算机科学 2025-06-02 Reza Asad , Reza Babanezhad , Issam Laradji , Nicolas Le Roux , Sharan Vaswani

We propose a new sample-efficient methodology, called Supervised Policy Update (SPU), for deep reinforcement learning. Starting with data generated by the current policy, SPU formulates and solves a constrained optimization problem in the…

机器学习 · 计算机科学 2018-12-27 Quan Vuong , Yiming Zhang , Keith W. Ross

Tremendous progress has been made in reinforcement learning (RL) over the past decade. Most of these advancements came through the continual development of new algorithms, which were designed using a combination of mathematical derivations,…

We introduce a novel policy learning method that integrates analytical gradients from differentiable environments with the Proximal Policy Optimization (PPO) algorithm. To incorporate analytical gradients into the PPO framework, we…

机器学习 · 计算机科学 2023-12-15 Sanghyun Son , Laura Yu Zheng , Ryan Sullivan , Yi-Ling Qiao , Ming C. Lin

Modern policy gradient algorithms, such as TRPO and PPO, outperform vanilla policy gradient in many RL tasks. Questioning the common belief that enforcing approximate trust regions leads to steady policy improvement in practice, we show…

机器学习 · 计算机科学 2025-05-27 Tao Wang , Ruipeng Zhang , Sicun Gao

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…

最优化与控制 · 数学 2019-11-27 Mingming Zhao , Yongfeng Li , Zaiwen Wen

Policy Mirror Descent (PMD) is a general family of algorithms that covers a wide range of novel and fundamental methods in reinforcement learning. Motivated by the instability of policy iteration (PI) with inexact policy evaluation, PMD…

最优化与控制 · 数学 2023-11-23 Emmeran Johnson , Ciara Pike-Burke , Patrick Rebeschini

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…

The policy gradient method enjoys the simplicity of the objective where the agent optimizes the cumulative reward directly. Moreover, in the continuous action domain, parameterized distribution of action distribution allows easy control of…

机器学习 · 计算机科学 2022-12-16 Md Masudur Rahman , Yexiang Xue

The goal of robust constrained reinforcement learning (RL) is to optimize an agent's performance under the worst-case model uncertainty while satisfying safety or resource constraints. In this paper, we demonstrate that strong duality does…

机器学习 · 计算机科学 2025-09-23 Shaocong Ma , Ziyi Chen , Yi Zhou , Heng Huang

This paper proposes a fast decentralized algorithm for solving a consensus optimization problem defined in a directed networked multi-agent system, where the local objective functions have the smooth+nonsmooth composite form, and are…

分布式、并行与集群计算 · 计算机科学 2017-03-28 Jinshan Zeng , Tao He , Mingwen Wang

Temporal credit assignment in reinforcement learning has long been a central challenge. Inspired by the multi-timescale encoding of the dopamine system in neurobiology, recent research has sought to introduce multiple discount factors into…

机器学习 · 计算机科学 2026-05-25 Jing Sun

We consider the problem of learning control policies that optimize a reward function while satisfying constraints due to considerations of safety, fairness, or other costs. We propose a new algorithm, Projection-Based Constrained Policy…

机器学习 · 计算机科学 2020-10-08 Tsung-Yen Yang , Justinian Rosca , Karthik Narasimhan , Peter J. Ramadge

Policy gradient methods are among the most effective methods in challenging reinforcement learning problems with large state and/or action spaces. However, little is known about even their most basic theoretical convergence properties,…

机器学习 · 计算机科学 2020-10-16 Alekh Agarwal , Sham M. Kakade , Jason D. Lee , Gaurav Mahajan

This paper develops the first policy gradient method with global optimality guarantee and complexity analysis for robust reinforcement learning under model mismatch. Robust reinforcement learning is to learn a policy robust to model…

机器学习 · 计算机科学 2022-05-17 Yue Wang , Shaofeng Zou

Decentralized optimization is a powerful paradigm that finds applications in engineering and learning design. This work studies decentralized composite optimization problems with non-smooth regularization terms. Most existing gradient-based…

最优化与控制 · 数学 2019-10-29 Sulaiman A. Alghunaim , Kun Yuan , Ali H. Sayed

Policy optimization methods are one of the most widely used classes of Reinforcement Learning (RL) algorithms. Yet, so far, such methods have been mostly analyzed from an optimization perspective, without addressing the problem of…

机器学习 · 计算机科学 2020-06-19 Yonathan Efroni , Lior Shani , Aviv Rosenberg , Shie Mannor

While the techniques in optimal control theory are often model-based, the policy optimization (PO) approach directly optimizes the performance metric of interest. Even though it has been an essential approach for reinforcement learning…

最优化与控制 · 数学 2022-11-23 Feiran Zhao , Keyou You , Tamer Başar