Stationary equilibria in discounted stochastic games with weakly interacting players.
Ulrich HorstPublished in: Games Econ. Behav. (2005)
Keyphrases
- stochastic games
- repeated games
- markov decision processes
- average reward
- infinite horizon
- nash equilibria
- games with incomplete information
- game theory
- long run
- optimal policy
- multiagent reinforcement learning
- nash equilibrium
- finite horizon
- reinforcement learning
- reinforcement learning algorithms
- dynamic programming
- incomplete information
- policy iteration
- game theoretic
- learning automata
- model free
- finite state
- markov decision process
- average cost
- genetic algorithm
- decision problems
- markov chain
- pure nash equilibria
- robust optimization
- single agent
- optimal control
- imperfect information
- search space
- multi agent