Markets News 

Learning to Trade with Reinforcement Learning

“There are many ways to speed up the training of Reinforcement Learning agents, including transfer learning, and using auxiliary tasks” reports wildml.com. In this post, I’m going to argue that training Reinforcement Learning agents to trade in the financial (and cryptocurrency) markets can be an extremely interesting research problem.When training Reinforcement Learning agents, it is often difficult or expensive to deploy them in the real world and get feedback.Selling works analogously, just that you are now operating on the bid side of the order book, and potentially moving the order book (and price) down.By matching with orders from the order book, you are taking away the option to trade to from other people – there’s less volume left!.
 
Source: wildml.com



Share This:

Related posts