Continuous On-line Evolution of Agent Behaviours with Cartesian Genetic Programming

TL;DR

This paper introduces an online evolutionary programming approach for continuous adaptation of agent behaviors, addressing a less-explored area outside evolutionary robotics, with a dedicated simulation testbed.

Contribution

It presents a novel online evolution algorithm for agent behavior adaptation and a testbed for evolutionary simulation outside robotics.

Findings

Demonstrates continuous behavioral adaptation in agents

Provides a new testbed for online evolutionary simulation

Highlights challenges and solutions for real-time agent evolution

Abstract

Evolutionary Computation has been successfully used to synthesise controllers for embodied agents and multi-agent systems in general. Notwithstanding this, continuous on-line adaptation by the means of evolutionary algorithms is still under-explored, especially outside the evolutionary robotics domain. In this paper, we present an on-line evolutionary programming algorithm that searches in the agent design space for the appropriate behavioural policies to cope with the underlying environment. We discuss the current problems of continuous agent adaptation, present our on-line evolution testbed for evolutionary simulation.