def RNN_optimization(X, Y, a_prev, parameters, alpha, vocab_size):

    # 1. Forward propagation
    loss_now, cache = RNN_forward_prop(X, Y, a_prev, parameters, vocab_size)

    # 2. Backward propagation
    grads, a = RNN_back_prop(X, Y, parameters, cache)

    # 3. Clip gradients
    grads = clip_grads(grads, 10)

    # 4. Update parameters
    parameters = update_parameters(parameters, grads, alpha)

    return loss_now, parameters, a[len(X)-1]