Efficient solutions for Mastermind using genetic algorithms
Computers and Operations Research
The number of pessimistic guesses in Generalized Mastermind
Information Processing Letters
Cracking bank PINs by playing mastermind
FUN'10 Proceedings of the 5th international conference on Fun with algorithms
Entropy-driven evolutionary approaches to the mastermind problem
PPSN'10 Proceedings of the 11th international conference on Parallel problem solving from nature: Part II
Improving and scaling evolutionary approaches to the mastermind problem
EvoApplications'11 Proceedings of the 2011 international conference on Applications of evolutionary computation - Volume Part I
Optimal analyses for 3×n AB games in the worst case
ACG'09 Proceedings of the 12th international conference on Advances in Computer Games
The number of pessimistic guesses in Generalized Black-peg Mastermind
Information Processing Letters
FUN'12 Proceedings of the 6th international conference on Fun with Algorithms
Comparing evolutionary algorithms to solve the game of mastermind
EvoApplications'13 Proceedings of the 16th European conference on Applications of Evolutionary Computation
Hi-index | 0.00 |
The MasterMind game involves decoding a secret code. The classic game is a code of six possible colors in four slots. The game has been analyzed and optimal strategies have been posed by computer scientists and mathematicians. In this paper we will survey previous work done on solving MasterMind, including several approaches using Genetic Algorithms. We will also analyze the solution sets and compare our results using a novel scoring system inside a GA against previous work using Genetic and Heuristic algorithms. Our GA is performing closer to optimal then previously published work. The GA we present is a Steady State GA using Fitness Proportional Reproduction (FPR), where the fitness function incorporates a simple heuristic algorithm. We also present a scoring method that is simpler then those used by other researchers. In larger games such as 10 colors and 8 slots our GA clearly outperform the heuristic algorithm. In fact if one wishes to tradeoff a higher average number of guesses to a faster running time, extremely large games such as 12 x10 can be solved in a reasonable time (i.e. minutes) of run time.