Google’s Deepmind AI learns to be your ultimate video game ally
AI models that play games go back decades, but they generally specialize in one game and always play to win.
From this data — and the annotations provided by data labelers — the model learns to associate certain visual representations of actions, objects, and interactions.
AI agents trained on multiple games performed better on games they hadn’t been exposed to.
But of course many games involve specific and unique mechanics or terms that will stymie the best-prepared AI.
And simple improvised actions or interactions are also being simulated and tracked by AI in some really interesting research into agents.
