As for poker, Google DeepMind selected heads-up no-limit Texas Maintain’em as its benchmark for this experiment. Game Arena is working like a heads-up poker tournament in between top AI models, with results feeding into a general public leaderboard. Google DeepMind is increasing its Game Arena platform to benchmark AI designs https://felixwumcq.canariblogs.com/the-smart-trick-of-game-arena-that-nobody-is-discussing-54823030