Online concurrent reinforcement learning algorithm to solve two‐player zero‐sum games for partially unknown nonlinear continuous‐time systems

DOI10.1002/ACS.2485zbMath1330.91013OpenAlexW1916670313MaRDI QIDQ5743779

Mohammad-Bagher Naghibi-Sistani, Ali Karimpour, Sholeh Yasini, Hamidreza Modares

Publication date: 8 February 2016

Published in: International Journal of Adaptive Control and Signal Processing (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1002/acs.2485

zbMATH Keywords

neural networks\(H_{\infty}\) controltwo-player zero-sum gamesonline concurrent reinforcement learning algorithm

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) 2-person games (91A05) Neural networks for/in biological studies, artificial life and related topics (92B20) Nonlinear systems in control theory (93C10) (H^infty)-control (93B36)

Related Items (5)

Optimal event‐triggered control for C‐T system with asymmetric constraints based on dual heuristic dynamic programing structure ⋮ Assured learning-enabled autonomy: a metacognitive reinforcement learning framework ⋮ Two-strategy evolutionary games with stochastic adaptive control ⋮ Predefined-time parameter estimation via modified dynamic regressor extension and mixing ⋮ Observer‐based adaptive optimal output containment control problem of linear heterogeneous Multiagent systems with relative output measurements

Cites Work

• Neural network approach to continuous-time direct adaptive optimal control for partially unknown nonlinear systems
• Integral reinforcement learning and experience replay for adaptive optimal control of partially-unknown constrained-input continuous-time systems
• Online actor-critic algorithm to solve the continuous-time infinite horizon optimal control problem
• A game theoretic algorithm to compute local stabilizing solutions to HJBI equations in nonlinear \(H_\infty \) control
• Galerkin approximations of the generalized Hamilton-Jacobi-Bellman equation
• L\(_2\)-gain and passivity techniques in nonlinear control
• Optimal control of unknown nonaffine nonlinear discrete-time systems based on adaptive dynamic programming
• Computationally efficient simultaneous policy update algorithm for nonlinearH_∞state feedback control with Galerkin's method
• Concurrent learning adaptive control of linear systems with exponentially convergent bounds
• Adaptive dynamic programming for online solution of a zero-sum differential game
• Adaptive Control Tutorial
• Feedback and optimal sensitivity: Model reference transformations, multiplicative seminorms, and approximate inverses
• L/sub 2/-gain analysis of nonlinear systems and nonlinear state-feedback H/sub infinity / control
• H/sub /spl infin control via measurement feedback for general nonlinear systems
• Successive Galerkin approximation algorithms for nonlinear optimal and robust control
• Computing the Positive Stabilizing Solution to Algebraic Riccati Equations With an Indefinite Quadratic Term via a Recursive Method
• Policy Iterations on the Hamilton–Jacobi–Isaacs Equation for $H_{\infty}$ State Feedback Control With Input Saturation
• Reinforcement Learning and Feedback Control: Using Natural Decision Methods to Design Optimal Adaptive Controllers
• The Method of Weighted Residuals and Variational Principles
• Online solution of nonlinear two‐player zero‐sum games using synchronous policy iteration

This page was built for publication: Online concurrent reinforcement learning algorithm to solve two‐player zero‐sum games for partially unknown nonlinear continuous‐time systems