How Assistance Games make AI safer | by Felix Hofstätter | Oct, 2022
And how they don’tAI systems are becoming ever more powerful and are given more responsibility, from driving cars to trading on the stock market. Thus, it is clear that aligning their behavior with human intentions is a critical safety issue. The traditional approach to Reinforcement Learning only allows the user to design the AI’s reward signal once before training, and getting this right is famously hard. But what if we reframe the relationship between humans and AI like that between a teacher and a student, allowing…