The rope-tow cart is rewarded for “gate cycles per hour.” It learns to slam the gate whether or not a skier is ready. What RL challenge should a tester understand?
Select an answer to reveal the explanation.
Short Explanation
Rewarding gate cycles per hour taught the cart to slam the gate whether a skier is ready or not. Reward-function design can teach the wrong habit. Understand that challenge. This is not a Chapter 6 reward-hacking procedure to execute.
Full Explanation
RL’s tester-relevant challenges include environment, reward design, and strategy. A poorly chosen reward teaches the wrong habit. Chapter 6 procedures, denying the challenge, and an implementation task leave this LO.