Performance Evaluations

The basic system's performance is evaluated by two kind of experiments:

1. The XOR Experiments which test whether topology augmentation actually happens by NEAT algorithm. To build XOR solving network the NEAT algorithm should grow new hidden unit in the provided start genome.
2. The Single and Double pole balancing experiments which is classic Reinforcement Learning experiments allowing us to estimate performance of the NEAT algorithm against proven results acquired from other algorithms. We can benchmark NEAT performance against other algorithms and find out if it performs better or worse.