AI in Human-computer Gaming: Techniques, Challenges and Opportunities

TL;DR

The paper surveys breakthroughs in AI for human-computer gaming across board, card, FPS, and RTS domains, detailing how tree-search augmented with deep networks (e.g., AlphaGo) and large-scale self-play RL (e.g., AlphaStar, OpenAI Five) have achieved professional-level play. It juxtaposes CFR-based approaches for imperfect information poker with deep RL and distributed training for complex, real-time games, highlighting both common frameworks and domain-specific adaptations. Key contributions include clarifying training pipelines (supervised pretraining, self-play, re-solving, league training), introducing mechanisms like nested subgame solving and continual transfer, and outlining challenges such as resource demands, evaluation criteria, and the need for new asymmetric and multi-agent testbeds. The work underscores the potential of general, scalable learning frameworks while signaling practical constraints and future directions toward big models, low-resource AI, and richer benchmarking in diverse gaming environments.

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 survey, we 1) compare the main difficulties among different kinds of games and the corresponding techniques utilized for achieving professional human level AIs; 2) summarize the mainstream frameworks and techniques that can be properly relied on for developing AIs for complex human-computer gaming; 3) raise the challenges or drawbacks of current techniques in the successful AIs; and 4) try to point out future trends in human-computer gaming AIs. Finally, we hope this brief review can provide an introduction for beginners, and inspire insights for researchers in the field of AI in human-computer gaming.

Figures (7)

• Figure 1: Games and AIs surveyed in this paper.
• Figure 2: A brief framework of AlphaGo series.
• Figure 3: A brief framework of Card game AIs.
• Figure 4: A brief framework of FTW for game CTF.
• Figure 5: A brief AI framework for typical RTS games.