Overfitting

Reinforcement learning agents have mastered games like Go that provide complete information about the state of the game to players. They’ve also excelled at Texas Hold ’Em poker, which provides incomplete information, as few cards are revealed.

When a model trains too much, it can overfit, or memorize, the training data, which reduces its ability to analyze similar-but-different inputs. But what if training continues? New work found that overfitting isn’t the end of the line.