中文
相关论文

相关论文: Off-policy Maximum Entropy Reinforcement Learning …

200 篇论文

This paper proposes a simulation-based reinforcement learning algorithm for controlling systems with uncertain and varying system parameters. While simulators are useful for safely learning control policies, the reality gap remains a major…

系统与控制 · 电气工程与系统科学 2026-05-14 Junya Ikemoto

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

A central challenge to applying many off-policy reinforcement learning algorithms to real world problems is the variance introduced by importance sampling. In off-policy learning, the agent learns about a different policy than the one being…

机器学习 · 计算机科学 2022-06-20 Eric Graves , Sina Ghiassian

Various methods for Multi-Agent Reinforcement Learning (MARL) have been developed with the assumption that agents' policies are based on accurate state information. However, policies learned through Deep Reinforcement Learning (DRL) are…

人工智能 · 计算机科学 2024-04-15 Songyang Han , Sanbao Su , Sihong He , Shuo Han , Haizhao Yang , Shaofeng Zou , Fei Miao

Advances in Reinforcement Learning (RL) have demonstrated data efficiency and optimal control over large state spaces at the cost of scalable performance. Genetic methods, on the other hand, provide scalability but depict hyperparameter…

机器学习 · 计算机科学 2021-01-19 Karush Suri , Xiao Qi Shi , Konstantinos N. Plataniotis , Yuri A. Lawryshyn

Value function factorization methods are commonly used in cooperative multi-agent reinforcement learning, with QMIX receiving significant attention. Many QMIX-based methods introduce monotonicity constraints between the joint action value…

机器学习 · 计算机科学 2025-04-11 Chang Huang , Shatong Zhu , Junqiao Zhao , Hongtu Zhou , Chen Ye , Tiantian Feng , Changjun Jiang

We propose a new algorithm, Mean Actor-Critic (MAC), for discrete-action continuous-state reinforcement learning. MAC is a policy gradient algorithm that uses the agent's explicit representation of all action values to estimate the gradient…

We present a new approach to the problems of evaluating and learning personalized decision policies from observational data of past contexts, decisions, and outcomes. Only the outcome of the enacted decision is available and the historical…

机器学习 · 统计学 2019-06-04 Nathan Kallus

Model-based reinforcement learning algorithms that combine model-based planning and learned value/policy prior have gained significant recognition for their high data efficiency and superior performance in continuous control. However, we…

机器学习 · 计算机科学 2025-02-07 Haotian Lin , Pengcheng Wang , Jeff Schneider , Guanya Shi

We study offline reinforcement learning in average-reward MDPs, which presents increased challenges from the perspectives of distribution shift and non-uniform coverage, and has been relatively underexamined from a theoretical perspective.…

机器学习 · 计算机科学 2026-04-23 Matthew Zurek , Guy Zamir , Yudong Chen

We establish an optimal sample complexity of $O(\epsilon^{-2})$ for obtaining an $\epsilon$-optimal global policy using a single-timescale actor-critic (AC) algorithm in infinite-horizon discounted Markov decision processes (MDPs) with…

机器学习 · 计算机科学 2026-05-08 Navdeep Kumar , Tehila Dahan , Lior Cohen , Ananyabrata Barua , Giorgia Ramponi , Kfir Yehuda Levy , Shie Mannor

This paper proposes an algorithm that aims to improve generalization for reinforcement learning agents by removing overfitting to confounding features. Our approach consists of a max-min game theoretic objective. A generator transfers the…

机器学习 · 计算机科学 2023-08-31 Md Masudur Rahman , Yexiang Xue

This paper studies the adaptive optimal stationary control of continuous-time linear stochastic systems with both additive and multiplicative noises, using reinforcement learning techniques. Based on policy iteration, a novel off-policy…

系统与控制 · 电气工程与系统科学 2021-12-07 Bo Pang , Zhong-Ping Jiang

Deep reinforcement learning has obtained significant breakthroughs in recent years. Most methods in deep-RL achieve good results via the maximization of the reward signal provided by the environment, typically in the form of discounted…

机器学习 · 计算机科学 2018-09-10 Yubin Deng , Ke Yu , Dahua Lin , Xiaoou Tang , Chen Change Loy

In reinforcement learning, agents that consider the context, or current state, when selecting source policies for transfer have been shown to outperform context-free approaches. However, none of the existing approaches transfer knowledge…

机器学习 · 计算机科学 2020-06-11 Michael Gimelfarb , Scott Sanner , Chi-Guhn Lee

In traditional reinforcement learning, an agent maximizes the reward collected during its interaction with the environment by approximating the optimal policy through the estimation of value functions. Typically, given a state s and action…

机器学习 · 计算机科学 2018-06-20 Shangda Li , Selina Bing , Steven Yang

Diffusion-based policies have recently shown strong results in robot manipulation, but their extension to multi-task scenarios is hindered by the high cost of scaling model size and demonstrations. We introduce Skill Mixture-of-Experts…

机器人学 · 计算机科学 2026-01-30 Ce Hao , Xuanran Zhai , Yaohua Liu , Harold Soh

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

In the field of reinforcement learning, because of the high cost and risk of policy training in the real world, policies are trained in a simulation environment and transferred to the corresponding real-world environment. However, the…

机器学习 · 计算机科学 2023-01-12 Takumi Tanabe , Rei Sato , Kazuto Fukuchi , Jun Sakuma , Youhei Akimoto

We study the problem of off-policy critic evaluation in several variants of value-based off-policy actor-critic algorithms. Off-policy actor-critic algorithms require an off-policy critic evaluation step, to estimate the value of the new…

机器学习 · 计算机科学 2019-12-12 Riashat Islam , Raihan Seraj , Samin Yeasar Arnob , Doina Precup
‹ 上一页 1 8 9 10 下一页 ›