Value Iteration for Simple Stochastic Games: Stopping Criterion and Learning Algorithm.
Edon KelmendiJulia KrämerJan KretínskýMaximilian WeiningerPublished in: CoRR (2018)
Keyphrases
- stochastic games
- learning algorithm
- stopping criterion
- markov decision processes
- average reward
- reinforcement learning algorithms
- state space
- reinforcement learning
- machine learning algorithms
- nash equilibrium
- infinite horizon
- nash equilibria
- search algorithm
- learning process
- dynamic programming
- edge detection
- optimal policy
- convergence rate
- machine learning