Developing game AI agent behaving like human by mixing reinforcement learning and supervised learning

Abstract

Artificial intelligence (AI) agent created with Deep Q-Networks (DQN) can defeat human agents in video games. Despite its high performance, DQN often exhibits odd behaviors, which could be immersion-breaking against the purpose of creating game AI. Moreover, DQN is capable of reacting to the game environment much faster than humans, making itself invincible… (More)
DOI: 10.1109/SNPD.2017.8022767

Topics

9 Figures and Tables

Cite this paper

@article{Miyashita2017DevelopingGA, title={Developing game AI agent behaving like human by mixing reinforcement learning and supervised learning}, author={Shohei Miyashita and Xinyu Lian and Xiao Zeng and Takashi Matsubara and Kuniaki Uehara}, journal={2017 18th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD)}, year={2017}, pages={489-494} }