A maximum principle for Markov regime-switching forward-backward stochastic differential games and applications.
Olivier Menoukeu PamenRomuald Hervé MomeyaPublished in: Math. Methods Oper. Res. (2017)
Keyphrases
- forward backward
- hidden markov models
- markov processes
- markov chain
- markov model
- monte carlo
- computer games
- stochastic process
- video games
- game theory
- monte carlo tree search
- nash equilibrium
- game design
- nash equilibria
- maximum number
- game playing
- learning automata
- perfect information
- markov process
- stochastic model
- energy dissipation
- game based learning
- semi markov
- weighted majority
- leader follower
- game tree search
- stochastic programming
- stochastic optimization
- reinforcement learning
- virtual environment
- probabilistic model
- search algorithm
- cooperative