my sine approximation during training works fine, while the prediction (which is feed by previous predictions, with a head start of 20 original values) does not approximate.
I guess there is a bug/misunderstanding in my prediction code A hint would be great.
Further testing showed that feeding the network with the predicted values (which have a slight deviation from the target values) cause to spiral the future values out of control. Using a more complex model and training for more episodes seems to solve the issue.