Neural Q-learning for discrete-time nonlinear zero-sum games with adjustable convergence rate.
Yuan WangDing WangMingming ZhaoNan LiuJunfei QiaoPublished in: Neural Networks (2024)
Keyphrases
- convergence rate
- learning rate
- convergence speed
- recurrent neural network model
- step size
- policy iteration
- network architecture
- reinforcement learning
- neural network
- primal dual
- wavelet neural network
- state space
- gradient method
- global convergence
- steady state error
- learning algorithm
- nonlinear systems
- markov chain
- mutation operator
- function approximation
- finite state
- optimal strategy
- action selection
- simulated annealing
- genetic algorithm ga