Nearly Optimal Control for Mixed Zero-Sum Game Based on Off-Policy Integral Reinforcement Learning.
Ruizhuo SongGaofu YangFrank L. LewisPublished in: IEEE Trans. Neural Networks Learn. Syst. (2024)
Keyphrases
- optimal control
- reinforcement learning
- control problems
- dynamic programming
- feedback control
- class of nonlinear systems
- stochastic games
- risk sensitive
- learning process
- control law
- rl algorithms
- control strategy
- brownian motion
- infinite horizon
- game theory
- learning algorithm
- optimal control problems
- function approximation
- markov decision processes
- actor critic
- reinforcement learning algorithms
- average cost
- state space
- lyapunov function
- optimal policy
- multi agent
- temporal difference
- data mining
- nash equilibrium