Eecient Reinforcement Learning through Symbiotic Evolution

This article presents a novel reinforcement learning method called SANE (Symbiotic, Adaptive Neuro-Evolution), which evolves a population of neurons through genetic algorithms to form a neural network capable of performing a task. Symbiotic evolution promotes both cooperation and specialization, which results in a fast, eecient genetic search and prevents convergence to subopti-mal solutions. In the inverted pendulum problem, SANE formed eeective networks 9 to 16 times faster than the Adaptive Heuristic Critic and 2 times faster than the GENITOR neuro-evolution approach without loss of generalization. Such eecient learning, combined with few domain assumptions , make SANE a promising approach to a broad range of reinforcement learning problems, including many real-world applications.