train_ddqn.py 文件源码

def replay(self):
        """Memory Management and training of the agent
        """
        if len(self.memory) < self.batch_size:
            return

        state, action, reward, next_state, done = self._get_batches()
        reward += (self.gamma
                   * np.logical_not(done)
                   * np.amax(self.model.predict(next_state), axis=1))
        q_target = self.target_model.predict(state)

        _ = pd.Series(action)
        one_hot = pd.get_dummies(_).as_matrix()
        action_batch = np.where(one_hot == 1)
        q_target[action_batch] = reward
        return self.model.fit(state, q_target,
                              batch_size=self.batch_size,
                              epochs=1,
                              verbose=False)