You've been logged out of GDC Vault since the maximum users allowed for this account has been reached. To access Members Only content on GDC Vault, please log out of GDC Vault from the computer which last accessed this account.

Click here to find out about GDC Vault Membership options for more users.

close
    
Session Name: Machine Learning Summit: Training and Improvement of Bots in Card Games, and Why Do We Need Them?
Speaker(s): Yiheng Zhou
Company Name(s): NetEase
Track / Format: Machine Learning Summit
Overview: The performance of bot players in a multiplayer online card game can have a significant impact on the player's experience, especially if the game mode is both confrontational and cooperative. However, the battle in this kind of game will be greatly affected by the randomness and information incompleteness brought by the game mechanism, which can increase the training difficulty of bot players. The speakers use cutting-edge artificial intelligence methods to train and improve bots in a card game, combining real player matchup data and reinforcement learning algorithms. They also discuss the impact of bot players on the user experience in multiplayer online games.

Game Developers Conference 2021

Yiheng Zhou

NetEase

free content

Machine Learning Summit

Programming