Reinforcement learning for exploratory linear-quadratic two-person zero-sum stochastic differential games.
Zhongshi SunGuangyan JiaPublished in: Appl. Math. Comput. (2023)
Keyphrases
- linear quadratic
- optimal control
- reinforcement learning
- stochastic games
- game theory
- nash equilibria
- reinforcement learning algorithms
- boolean games
- closed loop
- repeated games
- vector valued
- markov decision processes
- game theoretic
- dynamical systems
- nash equilibrium
- incomplete information
- average reward
- dynamic programming
- state space
- model free
- multi agent
- gaussian model
- game playing
- learning agent
- machine learning
- multiresolution
- control strategy
- transfer learning
- optimal policy
- control system
- real time