You learn preferences with a gradient bandit. Your average reward so far is R̄ = −19. This morning you cycle on a snowy morning and arrive in 30 minutes (reward −30). What happens to the preferences?

Question

Answer

Only H(Cycling) changes; the other preferences stay the same.

Answer

H(Cycling) decreases, and H(Tram) and H(Bus) increase.

Answer

None of the preferences change.

Answer

H(Cycling) increases, and H(Tram) and H(Bus) decrease.

Crowdly

You learn preferences with a gradient bandit. Your average reward so far is R̄ =...

Хочете миттєвий доступ до всіх перевірених відповідей на moodle.jku.at?