Data-driven adaptive dynamic programming for partially observable nonzero-sum games via Q-learning method

DOI10.1080/00207721.2019.1599463zbMath1486.91022OpenAlexW2927025417MaRDI QIDQ5025895

Min Wu, Wei Wang, Hao Fu, Xin Chen

Publication date: 7 February 2022

Published in: International Journal of Systems Science (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/00207721.2019.1599463

zbMATH Keywords

nonzero-sum gamesadaptive dynamic programming\(Q\)-learningpartially observable

Mathematics Subject Classification ID

Discrete-time games (91A50) Discrete-time control/observation systems (93C55) Dynamic programming (90C39) Networked control (93B70)

Related Items (2)

Model-free finite-horizon optimal control of discrete-time two-player zero-sum games ⋮ Learning output reference model tracking for higher-order nonlinear systems with unknown dynamics

Uses Software

• Approxrl

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Multi-player non-zero-sum games: online adaptive learning solution of coupled Hamilton-Jacobi equations
• Complete stability analysis of a heuristic approximate dynamic programming control design
• Event-triggered consensus control for discrete-time stochastic multi-agent systems: the input-to-state stability in probability
• Matrix Riccati equations in control and systems theory
• \({\mathcal Q}\)-learning
• Finite-time synchronization of uncertain coupled switched neural networks under asynchronous switching
• Multi-agent discrete-time graphical games and reinforcement learning solutions
• Distributed \(\mathcal H_{\infty}\) state estimation with stochastic parameters and nonlinearities through sensor networks: the finite-horizon case
• Optimal control of unknown nonaffine nonlinear discrete-time systems based on adaptive dynamic programming
• Nonzero-sum differential games
• Iterative algorithms for computing the feedback Nash equilibrium point for positive systems
• Finite-Horizon <inline-formula> <tex-math notation="TeX">${\cal H}_{\infty}$</tex-math></inline-formula> Control for Discrete Time-Varying Systems With Randomly Occurring Nonlinearities and Fading Measurements
• Finite-horizon differential games for missile–target interception system using adaptive dynamic programming with input constraints
• LMI-based approach to stability analysis for fractional-order neural networks with discrete and distributed delays
• Model-Free control performance improvement using virtual reference feedback tuning and reinforcement Q-learning
• Reinforcement Learning and Feedback Control: Using Natural Decision Methods to Design Optimal Adaptive Controllers

This page was built for publication: Data-driven adaptive dynamic programming for partially observable nonzero-sum games via Q-learning method