A note on semi-Markov perfect equilibria in discounted stochastic games.
Paulo BarelliJohn DugganPublished in: J. Econ. Theory (2014)
Keyphrases
- semi markov
- stochastic games
- games with incomplete information
- nash equilibria
- average reward
- markov decision processes
- long run
- repeated games
- infinite horizon
- nash equilibrium
- optimal policy
- game theory
- incomplete information
- reinforcement learning
- dynamic programming
- game theoretic
- conditional random fields
- finite horizon
- state space
- reinforcement learning algorithms
- average cost
- finite state
- markov chain
- policy iteration
- lower bound
- cooperative
- learning algorithm