As for poker, Google DeepMind selected heads-up no-limit Texas Keep’em as its benchmark for this experiment. Game Arena is jogging to be a heads-up poker tournament between main AI models, with final results feeding right into a general public leaderboard. Google DeepMind is expanding its Game Arena System to benchmark https://franciscojboam.dm-blog.com/40177539/getting-my-game-arena-to-work