Method predict

rl2/cartpole/q_learning_bins.py:64–66

(self, s)

    self.Q = np.random.uniform(low=-1, high=1, size=(num_states, num_actions))

  def predict(self, s):
    x = self.feature_transformer.transform(s)
    return self.Q[x]

  def update(self, s, a, G):
    x = self.feature_transformer.transform(s)