Event-Triggered Control of Discrete-Time Zero-Sum Games via Deterministic Policy Gradient Adaptive Dynamic Programming.
Yongwei ZhangBo ZhaoDerong LiuShunchao ZhangPublished in: IEEE Trans. Syst. Man Cybern. Syst. (2022)
Keyphrases
- dynamic programming
- policy gradient
- optimal control
- control system
- adaptive control
- actor critic
- reinforcement learning
- control problems
- markov chain
- markov decision processes
- control method
- control strategy
- finite state
- control strategies
- model free reinforcement learning
- machine learning
- function approximation
- heuristic search
- linear programming
- state space