Decentralized learning in general-sum matrix games: An LR-Ilagging anchor algorithm
This paper presents an LR-I lagging anchor algorithm that combines a lagging anchor method with an LR-I learning algorithm. We prove that this decentralized learning algorithm converges in strategies to Nash equilibria in two-player two-action general-sum matrix games. A practical LR-I lagging anchor algorithm is introduced for players to learn their Nash equilibrium strategies in general-sum stochastic games. Simulation results show the performance of the proposed LR-I lagging anchor algorithm in both matrix games and stochastic games.
|Keywords||Game theory, Matrix games, Multiagent learning|
|Journal||International Journal of Innovative Computing, Information and Control|
Lu, X. (Xiaosong), & Schwartz, H.M. (2013). Decentralized learning in general-sum matrix games: An LR-Ilagging anchor algorithm. International Journal of Innovative Computing, Information and Control, 9(1), 17–32.