Question: is it possible to implement a reinforcement learning model over a NodeJS server?
This server would be receiving binary forms of data (open /close; yes/no) in real time.
The objective for the model is to learn from the incoming data for a few days and then predict values for next day (similar to time series, but not exactly). The learned parameters need to be flushed every week.
Note: the training data I have doesn't allow for supervised learning - i.e. there is no data for the target class.