Leveraging LSTM and NEAT for enhanced performance in multi-agent evolutionary games

Nowadays, the application of deep learning in the field of evolutionary games has become a very popular topic. Humans use artificial intelligence as a powerful tool to predict the decision-making of multiple agents and to analyze it thoroughly, which can significantly reduce people's workload. Two of the most typical situations in game theory are the Iterated Prisoner's Dilemma (IPD) and the Iterated Snowdrift (ISD) games. In this paper, the Neuro Evolution of Augmenting Topologies (NEAT) algorithm is employed to perform population evolution in these two scenarios, and the Long Short-Term Memory (LSTM) model is utilized to predict the behavior of the population. The unique structure of the LSTM model contributes to its excellent predictive performance in forecasting the behavior of populations. Furthermore, this paper also investigates the changes in population intelligence and the frequency of cooperative behaviors during the process of population evolution, in order to explore the trends and specific proportions of different strategies as the population evolves.