Overfitting
Overlearning
Reward
None of above
Answer is Right!
Answer is Wrong!
The correct answer is C. Reward.
In reinforcement learning, a reward is a signal that tells an agent whether its actions are good or bad. The agent learns to take actions that lead to high rewards and avoid actions that lead to low rewards.
Overfitting is a problem in machine learning that occurs when a model learns the training data too well and is not able to generalize to new data. Overlearning is a similar problem that occurs when a human learner learns a task too well and is not able to adapt to changes in the task.
Neither overfitting nor overlearning are relevant to the question of what feedback is used in reinforcement learning.