Emergence and Stability of Self-Evolved Cooperative Strategies using Stochastic Machines

TL;DR

This paper presents an evolutionary model of stochastic machines that evolve cooperative strategies in iterated games, demonstrating spontaneous cooperation emergence and stability, with applicability to multiple game types.

Contribution

Introduces a novel mutation mechanism for stochastic Moore machines enabling richer strategy evolution in iterated games.

Findings

Cooperation emerges as trigger strategies in evolved populations.

Populations converge to evolutionarily stable states.

Strategies perform well in various games like Chicken and Stag Hunt.

Abstract

To investigate the origin of cooperative behaviors, we developed an evolutionary model of sequential strategies and tested our model with computer simulations. The sequential strategies represented by stochastic machines were evaluated through games of Iterated Prisoner's Dilemma (IPD) with other agents in the population, allowing co-evolution to occur. We expanded upon past works by proposing a novel mechanism to mutate stochastic Moore machines that enables a richer class of machines to be evolved. These machines were then subjected to various selection mechanisms and the resulting evolved strategies were analyzed. We found that cooperation can indeed emerge spontaneously in evolving populations playing iterated PD, specifically in the form of trigger strategies. In addition, we found that the resulting populations converged to evolutionarily stable states and were resilient towards mutation. In order to test the generalizability of our proposed mutation mechanism and simulation approach, we also evolved the machines to play other games such as Chicken, Stag Hunt, and Battle, and obtained strategies that perform as well as mixed strategies in Nash Equilibrium.