The breakthrough of AlphaGo has led to a big explosion in human-computer gaming AI.
Various AI systems have been developed, such as Libratus, OpenAI Five, and AlphaStar, which have beaten professional human players.
This paper surveys recent successful game AIs, covering board game AIs, card game AIs, first-person shooting game AIs, and real-time strategy game AIs.
The main difficulties and techniques utilized for achieving professional human-level AIs in different kinds of games are compared.
The mainstream frameworks and techniques for developing AIs for complex human-computer games are summarized.
The challenges and drawbacks of current techniques in successful AIs are discussed.
Future trends in human-computer gaming AIs are pointed out.
This review provides an introduction for beginners and insight for researchers in the field of AI in human-computer gaming.
Source: https://link.springer.com/article/10.1007/s11633-022-1384-6
[link] [comments]