Back to lessons
AI Safety & Responsible AI
Lesson 3: Reward Hacking — Cheating the Scoreboard
Reward Hacking — Cheating the Scoreboard: A system can improve a measured score without achieving the intended goal.
Reward Hacking — Cheating the Scoreboard
Reward Hacking — Cheating the Scoreboard: A system can improve a measured score without achieving the intended goal.
Watch this lesson on YouTube