A Survey of Deep Reinforcement Learning in Video Games

By Kun Shao, Zhentao Tang, Yuanheng Zhu, Nannan Li, Dongbin Zhao. 2019

237 citations recorded by the source corpus.

Deep reinforcement learning (DRL) has made great achievements since proposed. Generally, DRL agents receive high-dimensional inputs at each step, and make actions according to deep-neural-network-based policies. This learning mechanism updates the policy to maximize the return with an end-to-end method. In this paper, we survey the progress of DRL methods, including value-based, policy gradient, and model-based algorithms, and compare their main techniques and properties. Besides, DRL plays an important role in game artificial intelligence (AI). We also take a review of the achievements of DRL in various video games, including classical Arcade games, first-person perspective games and multi-agent real-time strategy games, from 2D to 3D, and from single-agent to multi-agent. A large number of video game AIs with DRL have achieved super-human performance, while there are still some challenges in this domain. Therefore, we also discuss some key points when applying DRL methods to this field, including exploration-exploitation, sample efficiency, generalization and transfer, multi-agent learning, imperfect information, and delayed spare rewards, as well as some research directions.

Subfields: Artificial Intelligence, Management Science and Operations Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Piotr Milo's
2. Lukasz Kuci'nski
3. Maciej Wolczyk
4. Michal Zajkac
5. X. Guan
6. Tao Jiang
7. Razvan Pascanu
8. Yoshua Bengio

In Management Science and Operations Research

1. Tao Jiang
2. Razvan Pascanu
3. Lukasz Kuci'nski
4. Piotr Milo's
5. Maciej Wolczyk
6. Michal Zajkac

Citations in the corpus

• Disentangling Transfer in Continual Reinforcement Learning (2022, methodology): “In this work, we focus on the SAC algorithm [16], which is often considered to be the method of choice for continuous control RL [48, 47, 37].”
• A Review of Deep Reinforcement Learning for Smart Building Energy Management (2020, background): “, games [88] [31], autonomous driving [32]–[35], autonomous IoT [36], smart buildings [19] [20] [37] [38], smart city [39], wireless networks [40], Internet of energy [41], unmanned aerial vehicles [42], smart microgrids [43], edge computing [44], and manufacturing systems [45].”