深度学习在游戏中的应用

综述了近年来发展迅速的深度学习技术及其在游戏(或博弈)中的应用. 深度学习通过多层神经网络来构建端对端的从输入到输出的非线性映射, 相比传统的机器学习模型有显见的优势. 最近, 深度学习被成功地用于解决强化学习中的策略评估和策略优化的问题, 并于多种游戏的人工智能取得了突破性的提高. 本文详述了深度学习在常见游戏中的应用.

Deep Learning Applied to Games

In this article, we present a survey of recent deep learning techniques and their applications to games. Deep learning aims to learn an end-to-end, non-linear mapping from the input to the output through multi-layer neural networks. Such architecture has several significant advantages as compared to traditional machine learning models. There has been a flurry of recent work on combining deep learning and reinforcement learning to better evaluate and optimize game policies, which has led to significant improvements of artificial intelligence in multiple games. We systematically review the use of deep learning in well-known games.