In Reinforcement Learning, what mechanism provides feedback to guide the agent's policy optimization?
Reinforcement learning agents learn optimal behavioral policies through trial-and-error interactions, guided by cumulative scalar reward signals.
What does the 'Exploration vs. Exploitation' dilemma signify in Reinforcement Learning?
The exploration-exploitation trade-off balances gathering new environmental knowledge against exploiting known high-reward choices.
In Reinforcement Learning, which model-free algorithm directly learns the optimal action-value function Q(s, a)?
Q-Learning is an off-policy temporal-difference algorithm that iteratively updates state-action values using the Bellman optimality equation.
What phenomenon occurs when a machine learning model fits training data noise too closely and fails to generalize to unseen test data?
Overfitting happens when a complex model memorizes the training data, capturing random statistical noise rather than generalizable underlying relationships.
Which characteristics identify an 'Underfitting' machine learning model?
Underfitting occurs when a model is too simplistic to capture the underlying structure, performing poorly on both training and test sets.