Skip to content
ml-recall

#contraction

1 question from Value-Based Methods

Timed test

1 question · 1 min · score and explanations at the end

Take a test
Q 1 / 1Score 0 / 0

Question 1: Short answer

mediumAI-checkedValue-Based Methods

For γ<1\gamma < 1, each sweep of value iteration shrinks the largest error max⁡s∣Vk(s)−V∗(s)∣\max_s |V_k(s) - V^*(s)| by at least a factor γ. If the initial error is 1 and γ=0.9\gamma = 0.9, how many sweeps guarantee an error of at most 0.01?

a whole number