On evolutionary selection of blackjack strategies

TL;DR

This paper uses evolutionary programming to optimize blackjack strategies, showing that random strategies evolve into profitable ones similar to known strategies within about a hundred generations.

Contribution

It demonstrates the effectiveness of evolutionary algorithms in deriving competitive blackjack strategies and compares evolved strategies to established ones.

Findings

Evolved strategies reach profitability after ~100 generations

Evolved strategies resemble known blackjack basic strategies

Starting from Thorp's strategy, evolution improves performance

Abstract

We apply the approach of evolutionary programming to the problem of optimization of the blackjack basic strategy. We demonstrate that the population of initially random blackjack strategies evolves and saturates to a profitable performance in about one hundred generations. The resulting strategy resembles the known blackjack basic strategies in the specifics of its prescriptions, and has a similar performance. We also study evolution of the population of strategies initialized to the Thorp's basic strategy.