☆ 4.7 Article

GPI-Based design for partially unknown nonlinear two-player zero-sum games

JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Computer Science, Artificial Intelligence

A Novel Value Iteration Scheme With Adjustable Convergence Rate

Mingming Ha et al.

Summary: In this article, a novel value iteration scheme is proposed, which introduces a relaxation factor and combines with other methods to accelerate and guarantee the convergence. The theoretical results and numerical examples demonstrate its fast convergence speed and stability.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2023)

添加到收藏夹

Article Automation & Control Systems

Asynchronous learning for actor-critic neural networks and synchronous triggering for multiplayer system

Ke Wang et al.

Summary: In this paper, a novel asynchronous learning algorithm with event communication is developed based on actor-critic neural network structure and reinforcement learning scheme to solve Nash equilibrium of multiplayer nonzero-sum differential game in an adaptive fashion. The proposed algorithm is substantiated on a four-player nonlinear system and applied to achieve adaptive cruise control in a nonlinear vehicle system, demonstrating its effectiveness.

ISA TRANSACTIONS (2022)

添加到收藏夹

Article Automation & Control Systems

Event-triggered distributed zero-sum differential game for nonlinear multi-agent systems using adaptive dynamic programming

Jingliang Sun et al.

Summary: This paper investigates an adaptive event-triggered distributed iterative differential game strategy for multi-agent systems, approximating the solution of coupled HJI equation with a critic neural network and designing a novel PE-free updating law. The developed strategy ensures the uniformly ultimately bounded of all closed-loop signals and avoids the Zeno behavior. The simulation results show a significant reduction in controller updates, saving computational and communication resources.

ISA TRANSACTIONS (2021)

添加到收藏夹

Article Automation & Control Systems

Adaptive Optimal Control of Linear Periodic Systems: An Off-Policy Value Iteration Approach

Bo Pang et al.

Summary: This article studies the infinite-horizon adaptive optimal control of continuous-time linear periodic systems and proposes a novel value iteration-based off-policy adaptive dynamic programming algorithm for a general class of systems. The algorithm is proven to uniformly converge to optimal solutions in both model-based and model-free cases, without assuming knowledge of an initial stabilizing controller. Application to a triple inverted pendulum demonstrates the feasibility and effectiveness of the proposed method.

IEEE TRANSACTIONS ON AUTOMATIC CONTROL (2021)

添加到收藏夹

Article Automation & Control Systems

Wasserstein Distributionally Robust Stochastic Control: A Data-Driven Approach

Insoon Yang

Summary: This article investigates the problem of control policy robustness and proposes a dynamic programming solution based on Wasserstein distribution. The study shows that the contraction property of Bellman operators can extend single-stage performance guarantees to multistage guarantees.

IEEE TRANSACTIONS ON AUTOMATIC CONTROL (2021)

添加到收藏夹

Article Automation & Control Systems

H∞ optimal control of unknown linear systems by adaptive dynamic programming with applications to time-delay systems

Huai-Yuan Jiang et al.

Summary: This paper proposes a new value iteration-based method to solve the H-infinity control problem of continuous-time linear systems by transforming it into solving a nonlinear differential equation. An iteration scheme based on value iteration method is proposed to approximate the optimal controller for H-infinity. The proposed scheme does not require special initial matrix or extra conditions, and provides a relatively small disturbance attenuation bound compared to existing results.

INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Zero-sum game-based neuro-optimal control of modular robot manipulators with uncertain disturbance using critic only policy iteration

Bo Dong et al.

Summary: This study introduces a novel neuro-optimal control method based on game theory and dynamic programming to solve the optimal trajectory tracking control problem of modular robot manipulators, ensuring bounded tracking errors and demonstrating the advantage and effectiveness of the control method through experiments.

NEUROCOMPUTING (2021)

添加到收藏夹

Article Automation & Control Systems

Event-Triggered Adaptive Dynamic Programming for Zero-Sum Game of Partially Unknown Continuous-Time Nonlinear Systems

Shan Xue et al.

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS (2020)

添加到收藏夹

Article Automation & Control Systems

Robust Optimal Control for Disturbed Nonlinear Zero-Sum Differential Games Based on Single NN and Least Squares

Ruizhuo Song et al.

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS (2020)

添加到收藏夹

Article Automation & Control Systems

Decentralised zero-sum differential game for a class of large-scale interconnected systems via adaptive dynamic programming

Jingliang Sun et al.

INTERNATIONAL JOURNAL OF CONTROL (2019)

添加到收藏夹

Article Automation & Control Systems

General value iteration based single network approach for constrained optimal controller design of partially-unknown continuous-time nonlinear systems

Geyang Xiao et al.

JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS (2018)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Optimal and Autonomous Control Using Reinforcement Learning: A Survey

Bahare Kiumarsi et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2018)

添加到收藏夹

Article Automation & Control Systems

Online adaptive policy iteration based fault-tolerant control algorithm for continuous-time nonlinear tracking systems with actuator failures

Kun Zhang et al.

JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS (2018)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Value and Policy Iterations in Optimal Control and Adaptive Dynamic Programming

Dimitri P. Bertsekas

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2017)

添加到收藏夹

Article Automation & Control Systems

Event-based H∞ consensus control for second-order leader-following multi-agent systems

Ji Han et al.

JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS (2016)

添加到收藏夹

Article Automation & Control Systems

On integral generalized policy iteration for continuous-time linear quadratic regulations

Jae Young Lee et al.

AUTOMATICA (2014)

添加到收藏夹

Article Automation & Control Systems

Computational adaptive optimal control for continuous-time linear systems with completely unknown dynamics

Yu Jiang et al.

AUTOMATICA (2012)

添加到收藏夹

Article Automation & Control Systems

Online solution of nonlinear two-player zero-sum games using synchronous policy iteration

Kyriakos G. Vamvoudakis et al.

INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL (2012)

添加到收藏夹

Article Automation & Control Systems

An iterative adaptive dynamic programming method for solving a class of nonlinear zero-sum differential games

Huaguang Zhang et al.

AUTOMATICA (2011)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.