Every day, millions of traders around the world are trying to make money by trading stocks. These days, physical traders are also being replaced by automated trading robots. Algorithmic trading market has experienced significant growth rate and large number of firms are using it. I have tried to build a Deep Q-learning reinforcement agent model to do automated stock trading.
In this model you set certain amounts of equities in the initial portfolio. Therefore, the agent can first start buying or selling equities. But some markets like forex, you can start buying or selling even without any position. Is it possible to design this kind of agents? Thank you very much!
I ran your code(aapl.us & amzn.us) and chose the models with good results(PnL). Then I used the same data(train data) to test the models. They almost get zero profit because of taking action two(do nothing). Do you have any idea about this problem?