# Adaptive Genomic Evolution of Neural Network Topologies (AGENT) for State-to-Action Mapping in Autonomous Agents

## TL;DR

This paper introduces AGENT, an improved neuroevolution method that adaptively evolves neural network topologies for better state-to-action mapping in autonomous agents, addressing stagnation and convergence issues.

## Contribution

It presents novel adaptive mechanisms integrated into NEAT to enhance neuroevolution efficiency and robustness in control tasks.

## Key findings

- Improved convergence and diversity control in neuroevolution.
- Enhanced performance on benchmark control problems.
- Successful application to UAV collision avoidance.

## Abstract

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.