Skip to content
ml-recall

#value-function

2 questions from RL Fundamentals, Policy Gradient & Actor-Critic

Timed test

2 questions · 2 min · score and explanations at the end

Take a test
Q 1 / 2Score 0 / 0

Question 1: Short answer

easyAI-checkedRL Fundamentals

In a TD-learning model of classical conditioning, a cue is followed a few steps later by a reward of 10 units that arrives with probability 0.8 (otherwise nothing), after which no further rewards follow in the trial. Values are learned with a small learning rate. What does the learned value of the state just before the reward converge to?

a number