How to solve large scale deterministic games with mean payoff by policy iteration.
Vishesh DhingraStephane GaubertPublished in: VALUETOOLS (2006)
Keyphrases
- policy iteration
- markov decision processes
- game theory
- nash equilibrium
- model free
- least squares
- fixed point
- repeated games
- reinforcement learning
- sample path
- optimal policy
- markov decision problems
- temporal difference
- payoff functions
- coalition structures
- average reward
- optimal control
- markov decision process
- stochastic games
- infinite horizon
- linear programming
- asymptotic analysis
- policy evaluation
- search space
- lower bound