Reinforcement Learning End Term: 13 April 2025, Set 1-5 (January 2025 term)

Assertion and Reason are both true and Reason is a correct explanation ofAssertion.

Assertion and Reason are both true and Reason is not a correct explanation ofAssertion.

Assertion is true but Reason is false.

Assertion is false but Reason is true.

Monte Carlo updates are unbiased estimators of the true value function, whileTD updates may introduce bias.

TD updates are guaranteed to converge to the optimal value function, whileMonte Carlo updates may not converge.

Monte Carlo updates require less memory and computational resourcescompared to TD updates.

TD updates are more robust to noise and stochasticity in the environmentcompared to Monte Carlo updates.

Maximization bias can lead to overestimation of action values, resulting insuboptimal policies and slower convergence to the optimal policy.

Maximization bias helps to accelerate learning by prioritizing actions withhigher estimated values, leading to faster convergence to the optimal policy.

Maximization bias reduces the exploration-exploitation trade-off, resulting inmore exploratory behavior and improved generalization to unseen states.

Maximization bias has minimal impact on the performance of Q-learning incomplex environments, as it tends to balance out over time through exploration.