Efficient Learning from Delayed Rewards through Symbiotic Evolution

David E. Moriarty, Risto Miikkulainen

Abstract: This paper presents a new reinforcement learning method called sane (Symbiotic, Adaptive Neuro-Evolution) that evolves a population of neurons through genetic algorithms to form a neural network for a given task. Symbiotic evolution promotes both cooperation and specialization in the population, which results in a fast, efficient genetic search and discourages convergence to suboptimal solutions. In the inverted pendulum problem, sane formed effective networks 9 to 16 times faster in CPU time than the Adaptive Heuristic Critic and 2 times faster than the GENITOR neuro-evolution approach without loss of generalization. Such efficient learning, combined with few domain assumptions, makes SANE a promising approach to a broad range of reinforcement learning problems, including many real-world applications.