4. (30 points) Reinforcement Learning (RL) a) How do model-based learning methods in RL work? b) How do model-free learning methods in RL work? c) We talked about the following example for the model-based learning? Explain this example. Input Policy Observed Episodes (Training) Learned Model Episode 1 Episode 2 T (s, a, s') A B, east, C, -1 B, east, C, -1 T(B, east, C) = 1.00 C, east, D, -1 C, east, D, -1 TIC, east, D) = 0.75 TIC, east, A) - 0.25 D, exit, X, +10 D, exit, X, +10 B CAD Episode 3 Episode 4 R(S, a, s') E E, north, C, -1 E, north, C, -1 R(B, east, C) = -1 C, east, D, -1 C, east, A, -1 RIC, east, D) = -1 R(D, exit, x) = +10 Assume: y = 1 D, exit, X, +10 A, exit, X, -10 No discounting UK