中文
相关论文

相关论文: PIPPS: Flexible Model-Based Policy Search Robust t…

200 篇论文

ReParameterization (RP) Policy Gradient Methods (PGMs) have been widely adopted for continuous control tasks in robotics and computer graphics. However, recent studies have revealed that, when applied to long-term reinforcement learning…

机器学习 · 计算机科学 2023-11-01 Shenao Zhang , Boyi Liu , Zhaoran Wang , Tuo Zhao

Traditional model-based reinforcement learning approaches learn a model of the environment dynamics without explicitly considering how it will be used by the agent. In the presence of misspecified model classes, this can lead to poor…

机器学习 · 计算机科学 2020-10-20 Pierluca D'Oro , Alberto Maria Metelli , Andrea Tirinzoni , Matteo Papini , Marcello Restelli

The policy gradient approach is a flexible and powerful reinforcement learning method particularly for problems with continuous actions such as robot control. A common challenge in this scenario is how to reduce the variance of policy…

机器学习 · 计算机科学 2013-01-18 Tingting Zhao , Hirotaka Hachiya , Voot Tangkaratt , Jun Morimoto , Masashi Sugiyama

Model-based Reinforcement Learning estimates the true environment through a world model in order to approximate the optimal policy. This family of algorithms usually benefits from better sample efficiency than their model-free counterparts.…

机器学习 · 计算机科学 2021-10-27 Valentin Charvet , Bjørn Sand Jensen , Roderick Murray-Smith

This paper considers the problem of learning safe policies in the context of reinforcement learning (RL). In particular, we consider the notion of probabilistic safety. This is, we aim to design policies that maintain the state of the…

机器学习 · 计算机科学 2023-04-20 Weiqin Chen , Dharmashankar Subramanian , Santiago Paternain

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

Diffusion models have gained prominence as powerful generative tools for solving inverse problems due to their ability to model complex data distributions. However, existing methods typically rely on complete knowledge of the forward…

机器学习 · 计算机科学 2026-03-03 Hongkun Dou , Zike Chen , Zeyu Li , Hongjue Li , Lijun Yang , Yue Deng

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

Model Predictive Path Integral (MPPI) control, Reinforcement Learning (RL), and Diffusion Models have each demonstrated strong performance in trajectory optimization, decision-making, and motion planning. However, these approaches have…

机器学习 · 计算机科学 2025-03-05 Yankai Li , Mo Chen

Policy gradient methods are extensively used in reinforcement learning as a way to optimize expected return. In this paper, we explore the evolution of the policy parameters, for a special class of exactly solvable POMDPs, as a…

机器学习 · 计算机科学 2020-11-04 Gavin McCracken , Colin Daniels , Rosie Zhao , Anna Brandenberger , Prakash Panangaden , Doina Precup

Constrained policy search (CPS) is a fundamental problem in offline reinforcement learning, which is generally solved by advantage weighted regression (AWR). However, previous methods may still encounter out-of-distribution actions due to…

机器学习 · 计算机科学 2024-02-29 Longxiang He , Li Shen , Linrui Zhang , Junbo Tan , Xueqian Wang

Direct optimization is an appealing framework that replaces integration with optimization of a random objective for approximating gradients in models with discrete random variables. A$^\star$ sampling is a framework for optimizing such…

机器学习 · 计算机科学 2020-10-26 Guy Lorberbom , Chris J. Maddison , Nicolas Heess , Tamir Hazan , Daniel Tarlow

Policy gradient methods are among the most effective methods for large-scale reinforcement learning, and their empirical success has prompted several works that develop the foundation of their global convergence theory. However, prior works…

机器学习 · 计算机科学 2020-12-25 Junzi Zhang , Jongho Kim , Brendan O'Donoghue , Stephen Boyd

Decision-making problems in uncertain or stochastic domains are often formulated as Markov decision processes (MDPs). Policy iteration (PI) is a popular algorithm for searching over policy-space, the size of which is exponential in the…

人工智能 · 计算机科学 2013-01-30 Yishay Mansour , Satinder Singh

Policy gradient methods, which have been extensively studied in the last decade, offer an effective and efficient framework for reinforcement learning problems. However, their performances can often be unsatisfactory, suffering from…

机器学习 · 计算机科学 2026-01-27 Shihab Ahmed , El Houcine Bergou , Aritra Dutta , Yue Wang

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

The problem of optimal motion planing and control is fundamental in robotics. However, this problem is intractable for continuous-time stochastic systems in general and the solution is difficult to approximate if non-instantaneous nonlinear…

机器人学 · 计算机科学 2017-02-28 Mustafa Mukadam , Ching-An Cheng , Xinyan Yan , Byron Boots

By framing reinforcement learning as a sequence modeling problem, recent work has enabled the use of generative models, such as diffusion models, for planning. While these models are effective in predicting long-horizon state trajectories…

机器人学 · 计算机科学 2024-09-26 Vineet Punyamoorty , Pascal Jutras-Dubé , Ruqi Zhang , Vaneet Aggarwal , Damon Conover , Aniket Bera

Model-based reinforcement learning methods often use learning only for the purpose of estimating an approximate dynamics model, offloading the rest of the decision-making work to classical trajectory optimizers. While conceptually simple,…

机器学习 · 计算机科学 2022-12-22 Michael Janner , Yilun Du , Joshua B. Tenenbaum , Sergey Levine

One of the key challenges that Reinforcement Learning (RL) faces is its limited capability to adapt to a change of data distribution caused by uncertainties. This challenge arises especially in RL systems using deep neural networks as…

机器学习 · 计算机科学 2025-06-17 Amornyos Horprasert , Esa Apriaskar , Xingyu Liu , Lanlan Su , Lyudmila S. Mihaylova
‹ 上一页 1 2 3 10 下一页 ›