An Approximate Dynamic Programming Approach to Repeated Games with Vector Losses.
Vijay KamblePatrick LoiseauJean C. WalrandPublished in: Oper. Res. (2024)
Keyphrases
- approximate dynamic programming
- repeated games
- linear program
- incomplete information
- dynamic programming
- stochastic games
- reinforcement learning
- nash equilibrium
- control policy
- step size
- average reward
- game theoretic
- average cost
- linear programming
- policy iteration
- special case
- machine learning
- game theory
- search space