交易策略的强化学习

你将学到什么

课程概况

This course is for finance professionals, investment management professionals, and traders. Alternatively, this Specialization can be for machine learning professionals who seek to apply their craft to trading strategies.

At the end of the course you will be able to do the following:

– Understand what reinforcement learning is and how trading is an RL problem
– Build Trading Strategies Using Reinforcement Learning (RL)
– Understand the benefits of using RL vs. other learning methods
– Differentiate between actor-based policies and value-based policies
– Incorporate RL into a momentum trading strategy

To be successful in this course, you should have a basic competency in Python programming and familiarity with the Scikit Learn, Statsmodels and Pandas library.You should have a background in statistics (expected values and standard deviation, Gaussian distributions, higher moments, probability, linear regressions) and foundational knowledge of financial markets (equities, bonds, derivatives, market structure, hedging).

课程大纲

Introduction to Course and Reinforcement Learning

In this module, reinforcement learning is introduced at a high level. The history and evolution of reinforcement learning is presented, including key concepts like value and policy iteration. Also, the benefits and examples of using reinforcement learning in trading strategies is described. We also introduce LSTM and AutoML as additional tools in your toolkit to use in implementing trading strategies.

Neural Network Based Reinforcement Learning

In the previous module, reinforcement learning was discussed before neural networks were introduced. In this module, we look at how reinforcement learning has been integrated with neural networks. We also look at LSTMs and how they can be applied to time series data.

Portfolio Optimization

In this module we discuss the practical steps required to create a reinforcement learning trading system. Also, we introduce AutoML, a powerful service on Google Cloud Platform for training machine learning models with minimal coding.