Stackelberg games for model-free continuous-time stochastic systems based on adaptive dynamic programming.
Xikui LiuYingying GeYan LiPublished in: Appl. Math. Comput. (2019)
Keyphrases
- model free
- stochastic systems
- dynamic programming
- reinforcement learning
- nash equilibria
- game theory
- sample path
- policy iteration
- optimal control
- state space
- leader follower
- function approximation
- temporal difference
- nash equilibrium
- average reward
- adaptive control
- markov decision processes
- dynamical systems
- stochastic models
- markov chain
- linear programming
- infinite horizon
- markov processes
- learning algorithm