Adaptability of Improved NEAT in Variable Environments
This work addresses the challenge of adaptability in AI for variable environments, but it is incremental as it builds on existing NEAT methods with specific modifications.
The paper tackled the problem of training control agents to adapt to variable environments by testing improved versions of NEAT, finding that recurrent connections significantly boosted performance while automatic feature selection harmed it and increased population size slightly reduced performance but lowered computation needs.
A large challenge in Artificial Intelligence (AI) is training control agents that can properly adapt to variable environments. Environments in which the conditions change can cause issues for agents trying to operate in them. Building algorithms that can train agents to operate in these environments and properly deal with the changing conditions is therefore important. NeuroEvolution of Augmenting Topologies (NEAT) was a novel Genetic Algorithm (GA) when it was created, but has fallen aside with newer GAs outperforming it. This paper furthers the research on this subject by implementing various versions of improved NEAT in a variable environment to determine if NEAT can perform well in these environments. The improvements included, in every combination, are: recurrent connections, automatic feature selection, and increasing population size. The recurrent connections improvement performed extremely well. The automatic feature selection improvement was found to be detrimental to performance, and the increasing population size improvement lowered performance a small amount, but decreased computation requirements noticeably.