LP formulation of asymmetric zero-sum stochastic games.
Lichun LiJeff S. ShammaPublished in: CDC (2014)
Keyphrases
- stochastic games
- robust optimization
- nash equilibria
- markov decision processes
- linear programming
- games with incomplete information
- repeated games
- average reward
- multi agent
- linear program
- reinforcement learning algorithms
- nash equilibrium
- semidefinite programming
- learning automata
- multiagent reinforcement learning
- mathematical programming
- incomplete information
- game theory
- dynamic programming