![]() “Our goal in this paper is not to chase state-of-the-art performance by any means necessary,” they wrote. ![]() The work comes from Noam Brown, Anton Bakhtin, Adam Lerer, and Qucheng Gong at Facebook. Poker is considered “an imperfect-information game.” According to the paper, previous self-learning AI had trouble with games like poker. Unlike chess, poker is a game where players don’t have access to all the important information. Versions of poker AI have been able to beat top human players in heads-up no-limit hold’em since 2017, when one called Libratus took down a group of elite poker pros. ![]() The bot is apparently even stronger than the 2019 poker AI called Pluribus. Similar to the AlphaZero program that has revolutionized the chess world to some extent, the new bot called ReBeL (short for Recursive Belief-based Learning) can achieve superhuman performance in heads-up no-limit hold’em through “self-play reinforcement learning.” ![]() Researchers at Facebook published a paper last week on a new poker AI that is apparently the most sophisticated to date and one that poses the greatest risk yet involving online poker play.
0 Comments
Leave a Reply. |