A menu of designs for reinforcement learning over time
Neural networks for control
Reinforcement learning-based output feedback control of nonlinear systems with input constraints
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
IEEE Transactions on Neural Networks
Online learning control by association and reinforcement
IEEE Transactions on Neural Networks
Brief paper: Adaptive optimal control for continuous-time linear systems based on policy iteration
Automatica (Journal of IFAC)
Reinforcement learning and adaptive dynamic programming for feedback control
IEEE Circuits and Systems Magazine
Generalized policy iteration for continuous-time systems
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Direct heuristic dynamic programming for nonlinear tracking control with filtered tracking error
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Adaptive dynamic programming: an introduction
IEEE Computational Intelligence Magazine
Automatica (Journal of IFAC)
ISNN'12 Proceedings of the 9th international conference on Advances in Neural Networks - Volume Part II
Automatica (Journal of IFAC)
Automatica (Journal of IFAC)
From model-based control to data-driven control: Survey, classification and perspective
Information Sciences: an International Journal
Reinforcement learning algorithms with function approximation: Recent advances and applications
Information Sciences: an International Journal
Hi-index | 22.16 |
In this paper, the optimal strategies for discrete-time linear system quadratic zero-sum games related to the H-infinity optimal control problem are solved in forward time without knowing the system dynamical matrices. The idea is to solve for an action dependent value function Q(x,u,w) of the zero-sum game instead of solving for the state dependent value function V(x) which satisfies a corresponding game algebraic Riccati equation (GARE). Since the state and actions spaces are continuous, two action networks and one critic network are used that are adaptively tuned in forward time using adaptive critic methods. The result is a Q-learning approximate dynamic programming (ADP) model-free approach that solves the zero-sum game forward in time. It is shown that the critic converges to the game value function and the action networks converge to the Nash equilibrium of the game. Proofs of convergence of the algorithm are shown. It is proven that the algorithm ends up to be a model-free iterative algorithm to solve the GARE of the linear quadratic discrete-time zero-sum game. The effectiveness of this method is shown by performing an H-infinity control autopilot design for an F-16 aircraft.