中文
相关论文

相关论文: Direct Policy Gradients: Direct Optimization of Po…

200 篇论文

Direct policy optimization in reinforcement learning is usually solved with policy-gradient algorithms, which optimize policy parameters via stochastic gradient ascent. This paper provides a new theoretical interpretation and justification…

机器学习 · 计算机科学 2023-10-24 Adrien Bolland , Gilles Louppe , Damien Ernst

Direct policy gradient methods for reinforcement learning are a successful approach for a variety of reasons: they are model free, they directly optimize the performance metric of interest, and they allow for richly parameterized policies.…

机器学习 · 计算机科学 2020-08-14 Alekh Agarwal , Mikael Henaff , Sham Kakade , Wen Sun

This paper discusses theoretical and experimental aspects of gradient-based approaches to the direct optimization of policy performance in controlled POMDPs. We introduce GPOMDP, a REINFORCE-like algorithm for estimating an approximation to…

机器学习 · 计算机科学 2025-12-08 Jonathan Baxter , Peter L. Bartlett

Reinforcement learning algorithms such as the deep deterministic policy gradient algorithm (DDPG) has been widely used in continuous control tasks. However, the model-free DDPG algorithm suffers from high sample complexity. In this paper we…

机器学习 · 计算机科学 2019-11-14 Qingpeng Cai , Ling Pan , Pingzhong Tang

We consider the joint design and control of discrete-time stochastic dynamical systems over a finite time horizon. We formulate the problem as a multi-step optimization problem under uncertainty seeking to identify a system design and a…

机器学习 · 计算机科学 2022-01-07 Adrien Bolland , Ioannis Boukas , Mathias Berger , Damien Ernst

We develop an optimization framework centered around a core idea: once a (parametric) policy is specified, control authority is transferred to the policy, resulting in an autonomous dynamical system. Thus we should be able to optimize…

机器学习 · 计算机科学 2025-06-11 Emo Todorov

Policy gradient methods are powerful reinforcement learning algorithms and have been demonstrated to solve many complex tasks. However, these methods are also data-inefficient, afflicted with high variance gradient estimates, and frequently…

机器学习 · 计算机科学 2019-05-15 Andreas Doerr , Michael Volpp , Marc Toussaint , Sebastian Trimpe , Christian Daniel

Reinforcement Learning (RL) has been used to finetune Large Language Models (LLMs) using a reward model trained from preference data, to better align with human judgment. The recently introduced direct alignment methods, which are often…

The goal of policy gradient approaches is to find a policy in a given class of policies which maximizes the expected return. Given a differentiable model of the policy, we want to apply a gradient-ascent technique to reach a local optimum.…

机器学习 · 计算机科学 2019-11-13 Mattis Manfred Kämmerer

Real-world control systems require policies that are not only high-performing but also interpretable and robust. A promising direction toward this goal is model-based control, which learns system dynamics and cost functions from historical…

系统与控制 · 电气工程与系统科学 2025-11-20 Yuexin Bian , Jie Feng , Yuanyuan Shi

Sample inefficiency is a long-lasting problem in reinforcement learning (RL). The state-of-the-art estimates the optimal action values while it usually involves an extensive search over the state-action space and unstable optimization.…

机器学习 · 计算机科学 2019-11-27 Kaixiang Lin , Jiayu Zhou

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

Deep Policy Gradient (PG) algorithms employ value networks to drive the learning of parameterized policies and reduce the variance of the gradient estimates. However, value function approximation gets stuck in local optima and struggles to…

机器学习 · 计算机科学 2023-02-21 Enrico Marchesini , Christopher Amato

Policy gradient (PG) methods are successful approaches to deal with continuous reinforcement learning (RL) problems. They learn stochastic parametric (hyper)policies by either exploring in the space of actions or in the space of parameters.…

机器学习 · 计算机科学 2024-05-31 Alessandro Montenegro , Marco Mussi , Alberto Maria Metelli , Matteo Papini

Stock portfolio optimization is the process of constant re-distribution of money to a pool of various stocks. In this paper, we will formulate the problem such that we can apply Reinforcement Learning for the task properly. To maintain a…

机器学习 · 计算机科学 2020-12-14 Le Trung Hieu

Policy optimization is a core component of reinforcement learning (RL), and most existing RL methods directly optimize parameters of a policy based on maximizing the expected total reward, or its surrogate. Though often achieving…

机器学习 · 计算机科学 2018-08-10 Ruiyi Zhang , Changyou Chen , Chunyuan Li , Lawrence Carin

Distributional reinforcement learning (DRL) is a recent reinforcement learning framework whose success has been supported by various empirical studies. It relies on the key idea of replacing the expected return with the return distribution,…

机器学习 · 计算机科学 2020-01-09 Rahul Singh , Keuntaek Lee , Yongxin Chen

This work adopts the very successful distributional perspective on reinforcement learning and adapts it to the continuous control setting. We combine this within a distributed framework for off-policy learning in order to develop what we…

The theory of continuous-time reinforcement learning (RL) has progressed rapidly in recent years. While the ultimate objective of RL is typically to learn deterministic control policies, most existing continuous-time RL methods rely on…

机器学习 · 计算机科学 2026-03-17 Ziheng Cheng , Xin Guo , Yufei Zhang

While policy optimization algorithms have played an important role in recent empirical success of Reinforcement Learning (RL), the existing theoretical understanding of policy optimization remains rather limited -- they are either…

机器学习 · 计算机科学 2023-12-05 Qinghua Liu , Gellért Weisz , András György , Chi Jin , Csaba Szepesvári
‹ 上一页 1 2 3 10 下一页 ›