Maswali ya Kuimarisha Mafunzo

Majibu na maelezo huonekana unapojibu maswali.

1. A warehouse robot tries an unfamiliar aisle to learn whether it shortens delivery time. Which side of the exploration–exploitation trade-off is this?
   • Exploration: testing an action whose value is uncertain
   • Exploitation: choosing the currently highest-valued action
   • Reward shaping: changing the objective after acting
   • Imitation: copying a labeled action
2. Rewards arrive as 2, 0 and 5 in a three-step episode. With discount factor 0.9, what is the return from the first step?
   • 7
   • 6.05
   • 6.5
   • 4.05
3. A designer raises gamma in a discounted-return objective. What changes?
   • The agent stops exploring
   • The reward function becomes a probability distribution
   • Future rewards count more relative to immediate rewards
   • Past rewards are counted again
4. A policy receives a reward only after a long sequence of actions. Which credit-assignment question arises?
   • Which input column has the longest name?
   • Whether every action must receive the same reward
   • Whether the final reward erases all prior observations
   • Which earlier actions contributed to the eventual outcome
5. A game agent earns points by collecting a harmless bonus, then ignores the mission because the bonus is easy to repeat. What failure does this illustrate?
   • Reward hacking: optimizing a proxy reward in a way that misses the intended goal
   • Catastrophic forgetting
   • Exploration collapse caused by gamma
   • A transition model error
6. A robot policy performs well in simulation. Why does it still need evaluation for its intended real deployment?
   • Simulation success proves every real-world action is safe
   • The simulator may rely on assumptions that fail outside it
   • A simulation prevents all reward loopholes
   • Real observations always match simulated ones
7. A delivery task has delayed payoffs: a longer route now may prevent a costly delay later. Why does a one-step reward view miss the trade-off?
   • It assumes every action is random
   • It cannot represent observations
   • It ignores consequences that arrive in later states
   • It forces rewards to be positive
8. A team changes the reward from “deliver safely” to “deliver quickly” and sees faster but riskier behavior. What should it conclude?
   • A faster policy proves the original safety objective was met
   • The discount factor alone guarantees safe behavior
   • Human preferences are unnecessary once training converges
   • Reward design affects behavior, so safety must be represented and evaluated explicitly