Packt+ | Advance your knowledge in tech

You're reading from Reinforcement Learning with TensorFlow A beginner's guide to designing self-learning systems with TensorFlow and OpenAI Gym

Product type Paperback

Published in Apr 2018

Publisher Packt

ISBN-13 9781788835725

Length 334 pages

Edition 1st Edition

Languages

Python

Tools

OpenAI Gym

Concepts

Reinforcement Learning

Author (1):

Sayon Dutta

View More author details

Table of Contents (17) Chapters

Preface

1. Deep Learning – Architectures and Frameworks

2. Training Reinforcement Learning Agents Using OpenAI Gym FREE CHAPTER

3. Markov Decision Process

4. Policy Gradients

5. Q-Learning and Deep Q-Networks

6. Asynchronous Methods

7. Robo Everything – Real Strategy Gaming

8. AlphaGo – Reinforcement Learning at Its Best

9. Reinforcement Learning in Autonomous Driving

10. Financial Portfolio Management

11. Reinforcement Learning in Robotics

12. Deep Reinforcement Learning in Ad Tech

13. Reinforcement Learning in Image Processing

14. Deep Reinforcement Learning in NLP

15. Further topics in Reinforcement Learning

16. Other Books You May Enjoy

Leave a review - let other readers know what you think

Data preparation

The trading experiment is tested in a cryptocurrency exchange called Poloniex. In order to test the current approach, m = 11 non-cash assets having the highest volume are pre-selected for the portfolio. Since the first base asset is cash, that is Bitcoin, the size of the portfolio is m+1 = 12. If we had tested in a market with larger volumes, such as foreign exchange market, there m would be as large as the total number of assets in the market.

Historical data of the assets is fed into a neural network, which outputs a portfolio weight vector. Input to a neural network at the end of period t is a tensor

, of rank 3 with shape (f, n, m), where:

m is the number of pre-selected non-cash assets
n is the number of input periods before t (here n = 50)
f=3 is the feature number

Since n = 50, that is, number of input periods is 50 and each period is of 30 minutes, the total time frame = 30*50 minutes = 1500 minutes = 25 hours. Features of the asset i on time period t are its closing...