Year: 2019
Type: preprint
Abstract: 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.
Source: arXiv (Cornell University)
Authors: Shao, Kun, Tang, Zhentao, Zhu, Yuanheng, Li, Nannan, Zhao, Dongbin
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Keywords: deep reinforcement learning, video game AI, game-playing agents, value-based methods, policy gradient, model-based reinforcement learning, arcade games, first-person games, real-time strategy games, multi-agent reinforcement learning, exploration-exploitation balance, sample efficiency, imperfect information, delayed rewards
Open Access status: green
OpenAlex ID: W2996726407
