I think classification problem cannot solve with reinforcement learning. I don't know what problem can solve with reinforcement learning. Is there a way to see if this problem can be solved with reinforcement learning?
Reinforcement Learning: Agents make a sequence of decisions through reward/penalty for the action performed
To answer your question yes RL can be used for classification
Though reinforcement learning can be utilized to solve classification problems it is not recommended.
- Reinforcement Learning takes long time to train
- Accuracy of Supervised Classification
>Accuracy of Reinforcement Learning
This paper can help you get started on the Reinforcement learning algorithms that can be used for solving classification problems
Video explanation of why not to go for RL for classification