Shoeboxam

environment = [4, 5, 7, 8];
expectation = 23;

% Initial weight
theta = 0.5;
theta_old = theta - 0.25;

while abs(theta - theta_old) > 1e-12
    % Derivative of squared error: ln = (expectation - reinforcement)^2
    dln_dr = -2 * (expectation - theta * environment);