AI in Human-computer Gaming: Techniques, Challenges and Opportunities
Qiyue Yin, Jun Yang, Kaiqi Huang, Meijing Zhao, Wancheng Ni, Bin, Liang, Yan Huang, Shu Wu, Liang Wang

TL;DR
This paper surveys recent advances in human-computer gaming AI, analyzing techniques, challenges, and future directions across various game types, highlighting progress and ongoing issues in achieving professional-level AI performance.
Contribution
It provides a comprehensive comparison of game-specific challenges, summarizes mainstream AI frameworks, and discusses future trends in human-computer gaming AI research.
Findings
Different game types pose unique challenges for AI development.
Current techniques can achieve professional-level performance in various games.
Identifies key challenges and potential future directions in the field.
Abstract
With breakthrough of the AlphaGo, human-computer gaming AI has ushered in a big explosion, attracting more and more researchers all around the world. As a recognized standard for testing artificial intelligence, various human-computer gaming AI systems (AIs) have been developed such as the Libratus, OpenAI Five and AlphaStar, beating professional human players. The rapid development of human-computer gaming AIs indicate a big step of decision making intelligence, and it seems that current techniques can handle very complex human-computer games. So, one natural question raises: what are the possible challenges of current techniques in human-computer gaming, and what are the future trends? To answer the above question, in this paper, we survey recent successful game AIs, covering board game AIs, card game AIs, first-person shooting game AIs and real time strategy game AIs. Through this…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsArtificial Intelligence in Games · Educational Games and Gamification · Reinforcement Learning in Robotics
MethodsGated Linear Unit · [LivE@PeRson]How do I talk to a real person at Expedia? · Bitcoin Customer Service Number +1-833-534-1729 · Multi-Head Attention · Attention Is All You Need · *Communicated@Fast*How Do I Communicate to Expedia? · Linear Layer · Batch Normalization · Tanh Activation · Max Pooling
