Как ввести массив в плотную нейронную сеть?

Question

Я пытаюсь построить глубокую обучающую нейронную сеть, но у меня возникают проблемы при вводе состояния игры в нейронную сеть. Я всегда получаю эту ошибку : ValueError: setting an array element with a sequence. Вот как выглядит состояниекак:

[[array([[3775.74129204, 1946.76168772],
       [3121.9310053 ,  699.72903429],
       [4366.58744074,  735.83476952]])
  array([[-2318.83417005,  1468.79312881],
       [-2212.77983243,   366.27498107]])
  array([[-3124.,   800.],
       [ -645.,   800.]]) -24.0]]

Полный код (это не полный класс, это просто важная вещь, которая создает проблему):

class DQNAgent:
    def __init__(self, state_size, action_size):
        self.state_size = state_size
        self.action_size = action_size
        self.memory = deque(maxlen=2000)
        self.gamma = 0.95    # discount rate
        self.epsilon = 1.0  # exploration rate
        self.epsilon_min = 0.01
        self.epsilon_decay = 0.995
        self.learning_rate = 0.001
        self.model = self._build_model()

    def _build_model(self):
        # Neural Net for Deep-Q learning Model
        model = Sequential()
        model.add(Dense(24, input_shape=(self.state_size,) ,activation='relu'))
        model.add(Dense(24, activation='relu'))
        model.add(Dense(self.action_size, activation='linear'))
        model.compile(loss='mse',
                      optimizer=Adam(lr=self.learning_rate))
        return model

    def remember(self, state, action, reward, next_state, done):
        self.memory.append((state, action, reward, next_state, done))
    def replay(self, batch_size):
        minibatch = random.sample(self.memory, batch_size)
        for state, action, reward, next_state, done in minibatch:
            target = reward
            if not done:
                print(next_state)
                target = (reward + self.gamma *
                          np.amax(self.model.predict(next_state)[0]))
            target_f = self.model.predict(state)
            target_f[0][action] = target
            self.model.fit(state, target_f, epochs=1, verbose=0)
        if self.epsilon > self.epsilon_min:
            self.epsilon *= self.epsilon_decay
if __name__ == "__main__":
    Init()
    done=False
    state_size=4
    action_size=4
    agent = DQNAgent(state_size, action_size)
    batch_size = 32
    EPISODES=50
    for e in range(EPISODES):
        for stpf in range(5):
            r_locs, i_locs, c_locs, ang, score = Game_step(1)
            state=np.array([r_locs, i_locs, c_locs,ang])
            state = np.reshape(state, [1, state_size])
        for stp in range(100):
            action =  agent.act(state)
            r_locs, i_locs, c_locs, ang, score = Game_step(action)
            next_state=np.array([r_locs, i_locs, c_locs,ang])
            reward=score
            next_state = np.reshape(next_state, [1, state_size])
            agent.remember(state, action, reward, next_state, done)
            state = next_state
            if len(agent.memory) > batch_size:
                agent.replay(batch_size)
        print("episode: {}/{}, score: {}".format(e, EPISODES))
        done=True

Как это исправить?Спасибо!