Evolving winning strategies for Nim-like games
This work addresses game strategy computation for Nim-like games, but it is incremental as it applies an existing evolutionary method to a specific domain.
The paper tackled the problem of computing winning strategies for Nim-like games by proposing an evolutionary approach using Multi Expression Programming, and reported that it is very suitable for this task with computational effort details provided.
An evolutionary approach for computing the winning strategy for Nim-like games is proposed in this paper. The winning strategy is computed by using the Multi Expression Programming (MEP) technique - a fast and efficient variant of the Genetic Programming (GP). Each play strategy is represented by a mathematical expression that contains mathematical operators (such as +, -, *, mod, div, and , or, xor, not) and operands (encoding the current game state). Several numerical experiments for computing the winning strategy for the Nim game are performed. The computational effort needed for evolving a winning strategy is reported. The results show that the proposed evolutionary approach is very suitable for computing the winning strategy for Nim-like games.