Online reinforcement learning multiplayer non-zero sum games of continuous-time Markov jump linear systems.
Xilin XinYidong TuVladimir StojanovicHai WangKaibo ShiShuping HeTianhong PanPublished in: Appl. Math. Comput. (2022)
Keyphrases
- linear systems
- markov chain
- dynamical systems
- reinforcement learning
- state space
- markov processes
- linear equations
- online game
- sufficient conditions
- imperfect information
- optimal control
- sparse linear systems
- computer games
- coefficient matrix
- markov decision processes
- input output
- learning algorithm
- neural network
- real time
- optimal policy
- nearest neighbor
- evolutionary algorithm
- objective function