Mean field stochastic games: Monotone costs and threshold policies.
Minyi HuangYan MaPublished in: CDC (2016)
Keyphrases
- stochastic games
- multiagent reinforcement learning
- optimal policy
- markov decision processes
- average reward
- average cost
- nash equilibria
- infinite horizon
- markov random field
- learning automata
- nash equilibrium
- upper bound
- multi agent
- finite state
- belief networks
- long run
- reinforcement learning algorithms
- robust optimization
- game theory
- repeated games
- total cost
- markov decision process
- imperfect information
- cooperative
- incomplete information
- single agent
- multistage
- multiagent systems
- dynamic programming