中文
相关论文

相关论文: Optimal-PhiBE: A PDE-based Model-free framework fo…

200 篇论文

In this paper, we study policy evaluation in continuous-time reinforcement learning (RL), where the state follows an unknown stochastic differential equation (SDE), but only discrete-time data are available. We first highlight that the…

最优化与控制 · 数学 2026-02-23 Yuhua Zhu

Model-based reinforcement learning (MBRL) approaches rely on discrete-time state transition models whereas physical systems and the vast majority of control tasks operate in continuous-time. To avoid time-discretization approximation of the…

机器学习 · 计算机科学 2021-06-14 Çağatay Yıldız , Markus Heinonen , Harri Lähdesmäki

This paper presents a new formulation for model-free robust optimal regulation of continuous-time nonlinear systems. The proposed reinforcement learning based approach, referred to as incremental adaptive dynamic programming (IADP),…

系统与控制 · 电气工程与系统科学 2022-03-25 Cong Li , Yongchao Wang , Fangzhou Liu , Qingchen Liu , Martin Buss

Continuous-time reinforcement learning (CTRL) provides a natural framework for sequential decision-making in dynamic environments where interactions evolve continuously over time. While CTRL has shown growing empirical success, its ability…

机器学习 · 计算机科学 2025-12-04 Runze Zhao , Yue Yu , Ruhan Wang , Chunfeng Huang , Dongruo Zhou

For continuous systems modeled by dynamical equations such as ODEs and SDEs, Bellman's Principle of Optimality takes the form of the Hamilton-Jacobi-Bellman (HJB) equation, which provides the theoretical target of reinforcement learning…

机器学习 · 计算机科学 2025-10-28 Haruki Settai , Naoya Takeishi , Takehisa Yairi

Reinforcement learning algorithms are typically designed for discrete-time dynamics, even though the underlying real-world control systems are often continuous in time. In this paper, we study the problem of continuous-time reinforcement…

机器学习 · 计算机科学 2026-03-03 Klemens Iten , Lenart Treven , Bhavya Sukhija , Florian Dörfler , Andreas Krause

Model-free reinforcement learning (RL) is a powerful approach for learning control policies directly from high-dimensional state and observation. However, it tends to be data-inefficient, which is especially costly in robotic learning…

机器人学 · 计算机科学 2020-10-14 Xubo Lyu , Mo Chen

Reinforcement learning (RL) is a promising method to solve control problems. However, model-free RL algorithms are sample inefficient and require thousands if not millions of samples to learn optimal control policies. A major source of…

机器学习 · 计算机科学 2022-10-31 Atish Dixit , Ahmed Elsheikh

We consider the problem of discounted optimal state-feedback regulation for general unknown deterministic discrete-time systems. It is well known that open-loop instability of systems, non-quadratic cost functions and complex nonlinear…

系统与控制 · 电气工程与系统科学 2020-03-31 Alexandros Tanzanakis , John Lygeros

Model-free reinforcement learning (RL) is a powerful, general tool for learning complex behaviors. However, its sample efficiency is often impractically large for solving challenging real-world problems, even with off-policy algorithms such…

机器学习 · 计算机科学 2020-02-25 Vitchyr Pong , Shixiang Gu , Murtaza Dalal , Sergey Levine

This paper establishes a rigorous connection between regularized discrete-time reinforcement learning (RL) and continuous-time stochastic optimal control. Specifically, classical RL algorithms are typically solving a regularized…

最优化与控制 · 数学 2026-04-24 Huyên Pham , Yuming Paul Zhang , Yuhua Zhu

This paper presents a model-free reinforcement learning (RL) algorithm to synthesize a control policy that maximizes the satisfaction probability of linear temporal logic (LTL) specifications. Due to the consideration of environment and…

形式语言与自动机理论 · 计算机科学 2022-01-04 Mingyu Cai , Shaoping Xiao , Baoluo Li , Zhiliang Li , Zhen Kan

Stabilizing a dynamical system is a fundamental problem that serves as a cornerstone for many complex tasks in the field of control systems. The problem becomes challenging when the system model is unknown. Among the Reinforcement Learning…

系统与控制 · 电气工程与系统科学 2026-01-30 Ankang Zhang , Ming Chi , Xiaoling Wang , Lintao Ye

This paper investigates the optimal control problem for a class of discrete-time stochastic systems subject to additive and multiplicative noises. A stochastic Lyapunov equation and a stochastic algebra Riccati equation are established for…

系统与控制 · 电气工程与系统科学 2020-08-24 Jing Lai , Junlin Xiong , Zhan Shu

Model-free algorithms are brought into the control system's research with the emergence of reinforcement learning algorithms. However, there are two practical challenges of reinforcement learning-based methods. First, learning by…

系统与控制 · 电气工程与系统科学 2024-09-18 Mi Zhou , Erik Verriest , Chaouki Abdallah

Recently, adaptive control systems with relaxed persistent excitation (PE) conditions have been proposed to guarantee true parameter convergence and improve the transient response. However, in some cases, sufficient control performance and…

系统与控制 · 电气工程与系统科学 2025-03-03 Satoshi Tsuruhara , Kazuhisa Ito

Model-based reinforcement learning (RL) is considered to be a promising approach to reduce the sample complexity that hinders model-free RL. However, the theoretical understanding of such methods has been rather limited. This paper…

机器学习 · 计算机科学 2021-02-16 Yuping Luo , Huazhe Xu , Yuanzhi Li , Yuandong Tian , Trevor Darrell , Tengyu Ma

In optimal control problem, policy iteration (PI) is a powerful reinforcement learning (RL) tool used for designing optimal controller for the linear systems. However, the need for an initial stabilizing control policy significantly limits…

最优化与控制 · 数学 2024-11-13 Zhen Pang , Shengda Tang , Jun Cheng , Shuping He

Model-free reinforcement learning attempts to find an optimal control action for an unknown dynamical system by directly searching over the parameter space of controllers. The convergence behavior and statistical properties of these…

最优化与控制 · 数学 2021-03-17 Hesameddin Mohammadi , Armin Zare , Mahdi Soltanolkotabi , Mihailo R. Jovanović

Preference-based reinforcement learning (PbRL) is an approach that enables RL agents to learn from preference, which is particularly useful when formulating a reward function is challenging. Existing PbRL methods generally involve a…

机器学习 · 计算机科学 2023-10-30 Gaon An , Junhyeok Lee , Xingdong Zuo , Norio Kosaka , Kyung-Min Kim , Hyun Oh Song
‹ 上一页 1 2 3 10 下一页 ›