问题
Here’s a general question that maybe someone could point me in the right direction.
I’m getting into Reinforcement Learning with Python 3.6/Tensorflow and I have found/tweaked my own model to train on historical data from a particular stock. My question is, is it possible to train this model on more than just one stock’s dataset? Every single machine learning article I’ve read on time series prediction and RL uses one dataset for training and testing, but my goal is to train a model on a bunch of tickers with varying prices in the hopes that the model can recognize similar price patterns, regardless of the price or ticker so that I could apply the trained model to a new dataset and it’ll work.
Right now it trains on one ticker and it’s prices, but when I try to add a new dataset for added training, it performs horribly because it doesn’t know the new prices, if that makes sense.
This is a basic question and I don’t necessarily expect a coded answer, just somewhere I could learn how to train a model using multiple datasets. I’m using OpenAI gym environment if that helps anything.
Thanks!
回答1:
Thanks to @Primusa I normalized my separate datasets by dividing each value by their respective maximums, then combined the datasets into one for training. Thanks!
回答2:
I think normalizing the dataset with % change from previous close on all datasets could be a good start. in that way, any stock with any price seems normalized.
来源:https://stackoverflow.com/questions/53974005/reinforcement-learning-using-multiple-stock-ticker-s-datasets