L-EARN

`reward = self.trades[-2]['total']*self.trades[-2]['current_price'] - self.trades[-2]['total']*self.trades[-1]['current_price']` should be ` reward = self.trades[-2]['total']*self.trades[-2]['current_price'] - self.trades[-1]['total']*self.trades[-1]['current_price']`

If you want, here is a little piece of code of my own. So yeah I'm trying to make a neural network who can hold the most profitable crypto. (Which...

> I also saw this but I wanted to finish the tutorial before making any change, and forgot later on, thx for the reminder You'll see how much harder it...