Question 36
In Markov Decision Processes (MDPs), what does the Bellman Optimality Equation for V*(s) state?
The Bellman Optimality Equation decomposes state value into maximum expected immediate reward plus discounted expected future state values.
In Markov Decision Processes (MDPs), what does the Bellman Optimality Equation for V*(s) state?
The Bellman Optimality Equation decomposes state value into maximum expected immediate reward plus discounted expected future state values.
Which algorithm computes optimal policy values in an MDP by iteratively executing sweep updates over all state values until convergence?
Value Iteration applies the Bellman optimality update operator iteratively across all states until value estimates converge.
Which unsupervised learning clustering algorithm partitions n observations into k clusters where each observation belongs to the cluster with the nearest mean?
K-Means minimizes within-cluster variance by iteratively assigning points to nearest centroids and recalculating centroid means.
In K-Nearest Neighbors (KNN) classification, what happens when K is chosen as 1?
$K=1 creates complex$, sensitive decision boundaries around every individual training point, causing high variance.
Which decision tree splitting criterion measures impurity based on the probability of incorrect classification of a randomly chosen element?
$Gini Impurity G = 1 - sum(p_{i}^2) calculates how often a randomly chosen element would be incorrectly labeled.$