Research Article
Limiting Dynamics for Q-Learning with Memory One in Symmetric Two-Player, Two-Action Games
Figure 10
Phase diagram for the possible BRNs in the prisoner’s dilemma for different values of : 0.1 (a), 0.3 (b), 0.75 (c), and 0.99 (d).
(a) |
(b) |
(c) |
(d) |