Evolutionary optimization of neural networks for reinforcement learning algorithms

摘要

In this paper we study the combination of two powerful approaches, evolutonary topology optimization (ENZO) and temporal dfiference learning (TD (#lambda#)) which is up to our knowledge the first time. Temporal difference learning was proven to be a well suited technique for learning strategies for solving reinforcement problems based on enrual network models, whereas evolutionary topology optimization is concurrently the most efficient network optimization technique. On two benchmarks, a labyrinth problem and the game Nine Men's Morris, the power of the approach is demonstrated. We concude that this combination of evolution and reinforcement learning algorithms is a suitable framework that uses the advantages of both methods leading to small and high performing networks for reinforcement problems.