A Weak Dynamic Programming Principle for Zero-Sum Stochastic Differential Games with Unbounded Controls.
Erhan BayraktarSong YaoPublished in: SIAM J. Control. Optim. (2013)
Keyphrases
- dynamic programming
- stochastic games
- game theory
- nash equilibria
- boolean games
- repeated games
- markov decision processes
- nash equilibrium
- learning automata
- game theoretic
- forward and backward
- perfect information
- incomplete information
- state space
- computer games
- stochastic optimization
- greedy algorithm
- video games
- stereo matching
- coarse to fine
- infinite horizon
- multistage
- cooperative
- dp matching
- optimal control
- reinforcement learning algorithms
- educational games
- reinforcement learning
- linear programming
- multi agent
- stochastic programming
- human computation
- learning games
- pure strategy
- multi agent systems