06279f054fcfa03517b1bd51ef156a9182af146f,PyPi/algorithms/td.py,DoubleQLearning,fit,#DoubleQLearning#Any#Any#,83

Before Change

        state, action, reward, next_state, absorbing, _ = parse_dataset(
            [dataset[-1]])

        sa = [state, action]

        approximator_idx = 0 if np.random.uniform() < 0.5 else 1

        q_current = self.approximator[approximator_idx].predict(sa)

After Change

        state, action, reward, next_state, absorbing, _ = parse_dataset(
            [dataset[-1]])

        sa = state_action(state, action)

        approximator_idx = 0 if np.random.uniform() < 0.5 else 1

        q_current = self.approximator[approximator_idx].predict(sa)

Instances