I want to perform a reinforcement learning experiment on top of an LSTM model.
The LSTM model performs an entity recognition on four entities (Products, Person, Location and others).
Now I want to use Tensorforce as an reinforcement learning engine along with my LSTM model for reinforcing misclassified events back into the model for a better model accuracy and performance.How can I achieve it ?
I came across Proximal Policy Optimisation? Is this what I should be using?