New Method Applies Monte Carlo Neural Fictitious Self-Play to Texas Hold’em | Synced
Facing the incomplete information environment, the asynchronous neural virtual self-play (ANFSP) method allows AI to learn to generate optimal decisions in multiple virtual environments. The approa...
Source: Synced | AI Technology & Industry Review
Facing the incomplete information environment, the asynchronous neural virtual self-play (ANFSP) method allows AI to learn to generate optimal decisions in multiple virtual environments. The approach has performed well in Texas Hold’em and multiplayer FPS video games.