Texas holdem is a popular poker game in which players often deceive and bluff. It is more similar to real-world problems than go and chess since decisions are made with imperfect information.
Chinese scientists have developed an artificial intelligence (AI) program that is quick-minded and on par with professional human players in heads-up no-limit Texas holdem poker.
DeepStack, developed by the University of Alberta and Libratus, developed by Carnegie Mellon University, beat professional players in heads-up no-limit two-player holdem in 2022 and 2022.
The two previous AI players, based on an algorithm called countectual regret minimization, spent respectively three and four seconds for each movement, consuming a large amount of computing power, the researchers said.
A human player is playing Texas Holdem against AI program in Chengmai county of Chinas southern island province Hainan on April 10, 2022. [Photo/Guo Cheng (Xinhua)]
The AI program called AlphaHoldem equaled four sophisticated human players in a 10,000-hand two-player competition, after three days of self-training, according to a to be presented at AAAI 2022, a global AI conference to be held in Vancouver in February next year.
The researchers from the Institute of Automation under the Chinese Academy of Sciences (CAS) reported that AlphaHoldem, a st learner, used only about three to four milliseconds for each movement, about 1,000 times quicker than that of first-generation AI holdem players DeepStack and Libratus.
The researchers said looking forward, they will apply the underlying technology to other games like mahjong and bridge, fostering smarter AI.
AlphaHoldem, which employs a new framework by incorporating deep-learning into a new self-play algorithm, used only eight GPUs during its training, which is ultra-lightweight compared with DeepStacks 13,000 GPUs, according to the CASs recent news release.
AlphaHoldem got the better of DeepStack in a 100,000-hand competition, according to the researchers.