NEAT Snake: a both evolutionary and neural network adaptation approach

Alisson Steffens Henrique, Vinicius Almeida dos Santos, Rodrigo Lyra


There are several challenges when modeling artificial intelligence
methods for autonomous players on games (bots). NEAT is one of
the models that, combining genetic algorithms and neural networks,
seek to describe a bot behavior more intelligently. In NEAT, a neural
network is used for decision making, taking relevant inputs from
the environment and giving real-time decisions. In a more abstract
way, a genetic algorithm is applied for the learning step of the neural
networks’ weights, layers, and parameters. This paper proposes the
use of relative position as the input of the neural network, based
on the hypothesis that the bot profit will be improved.

Texto completo:




  • Não há apontamentos.