Is recurrent neural network a reinforcement learning or supervised learning model?

Question

I just learn Machine learning and some ANN for a while and still need to figure it out the big picture of it. I'm still learning the basic and terminology to deepen my knowledge. I have learn about Reinforcement learning and what i understand (please correct me if i wrong) there 3 grouping method learning.

1. unsupervised (example for this is restricted boltzman machine)
2. supervised (CNN)
3. reinforcement (EKF, Particle Filter)

When I learn about recurrent net, some said that it belongs to supervised learning. But when i see how it works, it more suitable to said that it belong to reinforcement learning. can anyone clarify is recurrent net belong to supervised or reinforcement learning?

Answer 1

RNN is always used in supervised learning, because the core functionality of RNN requires labelled data sent in serially.

Now you must have seen RNN in RL too, but the catch is current deep reinforcement learning use the concept of supervised RNN which acts as a good feature vector for agent inside the RL ecosystem.

In simpler terms, the agent, the reward shaping, the environment everything is RL, but the way the deep network in agent learns is using RNN(or CNN or any type of ANN depending upon the problem statement).

So in short RNN always requires labelled data and hence supervised learning, but it can be used in RL environment too.