Evolution of Recurrent Neural Networks to Control Autonomous Life Agents

摘要

Studies of artificial life (alife) attempt to simulate simple living beings. On the other hand, autonomous agents researchers are interested in building agents that are able to complete a particular task without supervision. In this research, these two areas of artificial intelligence are combined into what we call "Autonomous Life Agent" (ALA). ALA is an artificial agent that is sent to some environment in which to live without any supervision or any predefined behaviour rules. The primary goal of the agent is to learn how to survive in its artificial environment. We utilize a recurrent neural network (RNN) to determine the agent's actions. A novel ALA Training System is developed that evolves RNN topology and link weights simultaneously using genetic algorithms.