Adaptive Genomic Evolution of Neural Network Topologies (AGENT) for State-to-Action Mapping in Autonomous Agents
This work addresses efficiency and reliability problems for researchers and practitioners using neuroevolution in autonomous agent control, though it is incremental relative to existing methods like NEAT.
The paper tackles premature stagnation and convergence issues in neuroevolution by introducing automated mechanisms to control population diversity and fitness improvement, achieving improved performance on benchmark problems including an Unmanned Aerial Vehicle collision avoidance task.
Neuroevolution is a process of training neural networks (NN) through an evolutionary algorithm, usually to serve as a state-to-action mapping model in control or reinforcement learning-type problems. This paper builds on the Neuro Evolution of Augmented Topologies (NEAT) formalism that allows designing topology and weight evolving NNs. Fundamental advancements are made to the neuroevolution process to address premature stagnation and convergence issues, central among which is the incorporation of automated mechanisms to control the population diversity and average fitness improvement within the neuroevolution process. Insights into the performance and efficiency of the new algorithm is obtained by evaluating it on three benchmark problems from the Open AI platform and an Unmanned Aerial Vehicle (UAV) collision avoidance problem.