Limiting Dynamics for Q-Learning with Memory One in Symmetric Two-Player, Two-Action Games

<div>All strategy pairs solve the Bellman equations self-consistently for the prisoner’s dilemma, their structural and behavioural types, the conditions for their existence, and the regions of Figure <a href="../fig2/">2</a> in which they exist.</div>

Complexity

tab1

Table 1

Table 1: Limiting Dynamics for Q-Learning with Memory One in Symmetric Two-Player, Two-Action Games 